© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 97764
    Prev
    Next
    INDEX
    Explanations

    Asset, parser, effect, Q, I

    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
    弥
    -0.85
     describe
    -0.73
     deck
    -0.70
     bu
    -0.69
    二百
    -0.69
     exec
    -0.68
     Schatten
    -0.67
    simplex
    -0.67
    راع
    -0.66
     Mar
    -0.66
    POSITIVE LOGITS
     Cuenta
    0.84
     Harg
    0.78
    Conclusión
    0.77
    ーい
    0.77
    ᭄
    0.77
     Account
    0.76
    statusText
    0.74
     zoude
    0.74
     Katy
    0.74
    selli
    0.73
    Activations Density 0.014%

    No Known Activations