© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27102
    Prev
    Next
    INDEX
    Explanations

    aqueous solutions and environments

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

    references to aqueous solutions or water in scientific contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     deliciously
    -1.36
    
    -1.35
    𓁹
    -1.27
    さぁ
    -1.26
    ghế
    -1.26
    骉
    -1.25
    だけでなく
    -1.23
    すごく
    -1.23
    鲼
    -1.23
     colossal
    -1.22
    POSITIVE LOGITS
     or
    1.59
     although
    1.41
     varför
    1.36
    There
    1.30
    Some
    1.24
    Despite
    1.22
     Although
    1.22
     betyr
    1.20
     despite
    1.20
    Although
    1.20
    Activations Density 0.033%

    No Known Activations