© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 54210
    Prev
    Next
    INDEX
    Explanations

    businesscompaniespatientsprocedure

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

    write a story or description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     словам
    0.51
    ሰራ
    0.51
    鹳
    0.49
     Using
    0.49
    inicio
    0.49
     संयोग
    0.48
     ఆలో
    0.48
     질문
    0.47
    要去
    0.47
     заместитель
    0.47
    POSITIVE LOGITS
    ’
    0.54
    '
    0.52
    ！】
    0.47
    </th>
    0.46
    ']],
    0.45
     unprofitable
    0.44
    <?>
    0.44
     honing
    0.44
     tandis
    0.43
    ۞
    0.42
    Activations Density 0.000%

    No Known Activations