© 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. 34-GEMMASCOPE-RES-131K
    7. 31345
    Prev
    Next
    INDEX
    Explanations

    color definitions and values

    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
     november
    -0.98
     November
    -0.93
     might
    -0.83
     ide
    -0.82
     last
    -0.82
     did
    -0.81
     fa
    -0.80
     divul
    -0.79
     at
    -0.79
     či
    -0.79
    POSITIVE LOGITS
     Poincar
    0.94
     juven
    0.91
     gins
    0.86
     ehemal
    0.84
     トート
    0.84
     việc
    0.83
     whitelist
    0.83
    белый
    0.82
     echip
    0.82
    タレ
    0.81
    Activations Density 0.006%

    No Known Activations