© 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. 64083
    Prev
    Next
    INDEX
    Explanations

    numbers followed by markdown table separators

    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
     blau
    -0.98
    grafie
    -0.91
     Nederlandse
    -0.90
    fiets
    -0.89
    思います
    -0.85
     echte
    -0.85
    >_
    -0.85
     schild
    -0.85
     dizer
    -0.84
    weakSelf
    -0.84
    POSITIVE LOGITS
    There
    0.93
     Noida
    0.84
    Through
    0.82
    With
    0.81
    While
    0.81
    からも
    0.80
     защото
    0.80
    Numerous
    0.78
    Moreover
    0.78
     Theore
    0.78
    Activations Density 0.007%

    No Known Activations