© 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. 57347
    Prev
    Next
    INDEX
    Explanations

    and conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     Angele
    -0.83
    ほうがいい
    -0.83
     vantagens
    -0.78
     economically
    -0.74
     情報
    -0.73
    サム
    -0.73
     Bienen
    -0.73
     dniu
    -0.72
     neler
    -0.72
     aprire
    -0.71
    POSITIVE LOGITS
     and
    3.27
     και
    2.22
    และ
    2.17
     và
    2.14
     и
    2.14
     și
    1.94
    and
    1.70
     şi
    1.66
     और
    1.64
     &&
    1.51
    Activations Density 0.472%

    No Known Activations