© 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. 10-GEMMASCOPE-RES-131K
    7. 8404
    Prev
    Next
    INDEX
    Explanations

    requests for comments

    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_10/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
    に関する
    -1.16
     ambienta
    -1.16
     reino
    -1.16
     secr
    -1.16
    ības
    -1.14
     نوشته
    -1.10
     urusan
    -1.09
     вони
    -1.09
    himself
    -1.08
     inspirasi
    -1.08
    POSITIVE LOGITS
     either
    1.56
    клада
    1.24
     другим
    1.20
     who
    1.19
     that
    1.19
     igény
    1.17
     /*
    1.16
     innym
    1.16
     our
    1.16
     Either
    1.15
    Activations Density 0.051%

    No Known Activations