© 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. 93391
    Prev
    Next
    INDEX
    Explanations

    Related literature, TABLE, Q, Suberin, Kabru

    np_acts-logits-general · gemini-2.5-flash-lite

    headers, titles, and formatting elements in structured documents.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     Condom
    -0.82
     frond
    -0.79
     tweeter
    -0.78
    Desa
    -0.77
    ﻢ
    -0.75
     goblet
    -0.75
    otre
    -0.75
     Lute
    -0.75
     noct
    -0.74
     SETUP
    -0.74
    POSITIVE LOGITS
     AD
    0.94
    AD
    0.81
     deposits
    0.80
    的内容
    0.78
     rely
    0.75
    unton
    0.75
     Putih
    0.73
    forestry
    0.73
    pian
    0.72
    Rcpp
    0.72
    Activations Density 0.005%

    No Known Activations