© 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. 77237
    Prev
    Next
    INDEX
    Explanations

    RPG dice and systems

    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
    ietf
    -0.88
    Diagnostics
    -0.83
    DIY
    -0.81
     receive
    -0.73
     DIY
    -0.71
    jzen
    -0.69
    jä
    -0.69
     play
    -0.69
    ModelState
    -0.68
    DSC
    -0.68
    POSITIVE LOGITS
     cull
    0.82
     percentile
    0.79
     TAT
    0.72
    PLICATION
    0.71
    chung
    0.71
     Fudge
    0.70
     Perc
    0.69
     Cary
    0.69
     Shaped
    0.69
    BOT
    0.68
    Activations Density 0.021%

    No Known Activations