© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117437
    Prev
    Next
    INDEX
    Explanations

    solubility and dissolution

    np_acts-logits-general · gemini-2.5-flash-lite

    words related to solubility or dissolution of substances.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron activates on terms related to solubility and dissolution (e.g., soluble, solubility, solubilization, dissolved).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fixé
    -0.87
     Penggunaan
    -0.84
    ffen
    -0.80
    ΟΝ
    -0.79
     Archite
    -0.77
     WPF
    -0.76
    军队
    -0.75
     молоко
    -0.75
     breathes
    -0.75
     VIL
    -0.75
    POSITIVE LOGITS
     solubility
    1.18
     sol
    0.84
     Action
    0.81
     dissolution
    0.79
     in
    0.79
     dissolving
    0.78
     salts
    0.77
     magát
    0.76
    ErrorMsg
    0.75
     sparingly
    0.75
    Activations Density 0.031%

    No Known Activations