© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 2062
    Prev
    Next
    INDEX
    Explanations

    analyst performance

    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
    ClientID
    -0.83
     preen
    -0.79
     SAU
    -0.74
     vial
    -0.73
    trieb
    -0.72
    関連項目
    -0.71
     INSERT
    -0.71
     pren
    -0.71
     mihi
    -0.71
     AHEAD
    -0.71
    POSITIVE LOGITS
     analysts
    4.19
     analyst
    4.06
     Analysts
    3.44
    Analysts
    3.31
     Analyst
    2.98
    analyst
    2.91
    Analyst
    2.80
     Wall
    2.23
    analy
    2.20
    Wall
    2.08
    Activations Density 0.028%

    No Known Activations