© 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. 57972
    Prev
    Next
    INDEX
    Explanations

    citations with years

    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
     in
    -1.36
     it
    -1.27
     said
    -1.19
     from
    -1.18
     It
    -1.13
     to
    -1.13
     at
    -1.12
     with
    -1.09
     and
    -1.06
     according
    -1.06
    POSITIVE LOGITS
    Pilih
    1.34
     sécher
    1.33
     graisse
    1.28
     autre
    1.27
     rapporter
    1.27
    ۲
    1.27
    Informasi
    1.27
     cóc
    1.26
    Daha
    1.24
     tromper
    1.23
    Activations Density 0.231%

    No Known Activations