© 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. 117492
    Prev
    Next
    INDEX
    Explanations

    staying or visiting places recently

    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
     either
    -1.20
     where
    -1.18
     that
    -1.16
    addEventListener
    -1.16
     wherever
    -1.12
     those
    -1.12
     لاع
    -1.07
    begin
    -1.05
    handeling
    -1.05
    <tr>
    -1.04
    POSITIVE LOGITS
     recently
    1.35
     Saturday
    1.34
     last
    1.31
     yesterday
    1.23
     recent
    1.20
     late
    1.17
     Sunday
    1.09
     recientemente
    1.06
     unseres
    1.06
     unplanned
    1.03
    Activations Density 0.013%

    No Known Activations