© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 39637
    Prev
    Next
    INDEX
    Explanations

    Gay & Lesbian Chamber

    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_10/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
     dokumenta
    -1.55
    ⢐
    -1.54
    噲
    -1.48
     опять
    -1.45
    ﻳ
    -1.45
     pourraient
    -1.45
    selbe
    -1.43
     rafra
    -1.42
     skry
    -1.42
     construit
    -1.42
    POSITIVE LOGITS
     these
    1.65
    }{
    1.61
     on
    1.56
    3
    1.54
    and
    1.54
    4
    1.53
     in
    1.53
    0
    1.49
    S
    1.47
    ;
    
    1.46
    Activations Density 0.153%

    No Known Activations