© 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. 22-GEMMASCOPE-RES-131K
    7. 66109
    Prev
    Next
    INDEX
    Explanations

    creating, collecting, distributing, or finding items

    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_22/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
     repuesto
    -1.19
    ❣
    -1.17
     luigi
    -1.13
     maanden
    -1.05
     procéder
    -1.04
    ATIVA
    -1.02
    •.
    -1.00
     Bár
    -1.00
     ♡
    -0.99
     proced
    -0.99
    POSITIVE LOGITS
     for
    1.98
     from
    1.29
     those
    1.23
    alians
    1.20
    などを
    1.14
    などは
    1.11
    ઃ
    1.09
     a
    1.07
    怎样的
    1.06
     نہیں
    1.02
    Activations Density 0.078%

    No Known Activations