© 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. 63415
    Prev
    Next
    INDEX
    Explanations

    quote and word

    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
    ieš
    -1.02
    lecte
    -0.95
    様々な
    -0.93
    __::
    -0.93
    ður
    -0.93
    جين
    -0.92
     troch
    -0.91
     vilja
    -0.91
    ificado
    -0.91
    ・・・
    -0.91
    POSITIVE LOGITS
     you
    1.92
     listen
    1.64
     look
    1.52
     okay
    1.46
     let
    1.45
     yeah
    1.34
     guys
    1.34
     maybe
    1.33
     OK
    1.33
    listen
    1.31
    Activations Density 0.006%

    No Known Activations