© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1327
    Prev
    Next
    INDEX
    Explanations

    source attribution

    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
    važ
    -0.70
    TOF
    -0.69
    เกม
    -0.68
     bibl
    -0.67
    inetti
    -0.67
    uC
    -0.66
     bikers
    -0.65
     trụ
    -0.64
    リー
    -0.63
    Bus
    -0.63
    POSITIVE LOGITS
     Truppen
    0.82
     bå
    0.77
    Konst
    0.71
     desirability
    0.70
    NickName
    0.70
     spiller
    0.70
     replies
    0.70
    żenia
    0.69
    ᱛ
    0.69
     Nazare
    0.69
    Activations Density 0.102%

    No Known Activations