© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 15359
    Prev
    Next
    INDEX
    Explanations

    instructions and needs

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

    The neuron specializes in spotting floating‐point numeric values (decimal numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    s
    0.89
    ss
    0.86
    ts
    0.86
    U
    0.84
    uan
    0.84
    uff
    0.82
    D
    0.82
    H
    0.82
    saa
    0.81
    tered
    0.79
    POSITIVE LOGITS
     SQLAlchemy
    0.96
     basilaires
    0.95
    Спољашње
    0.90
     liées
    0.90
     brahm
    0.88
     couvertures
    0.88
     protéines
    0.87
     GoName
    0.87
     Continuando
    0.86
     nommé
    0.85
    Activations Density 0.000%

    No Known Activations