© 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. 57665
    Prev
    Next
    INDEX
    Explanations

    backup retention

    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
    Ses
    -0.86
     Ses
    -0.84
    hone
    -0.73
     Bobby
    -0.71
    biter
    -0.70
     fragrant
    -0.69
     thanks
    -0.69
     cucchiai
    -0.69
    ────────
    -0.68
    Bobby
    -0.68
    POSITIVE LOGITS
     vaults
    0.87
     Tiktok
    0.82
     vault
    0.79
     retainer
    0.77
    晚了
    0.76
    녁
    0.74
     Determin
    0.74
     Consulate
    0.73
     Sarmiento
    0.73
    ctibles
    0.73
    Activations Density 0.009%

    No Known Activations