© 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. 23538
    Prev
    Next
    INDEX
    Explanations

    Feats and abilities

    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
     znacznie
    -0.74
     Safety
    -0.73
    BeginInit
    -0.69
    𝗯
    -0.69
    ைக
    -0.69
     Stunde
    -0.69
    pplung
    -0.68
     Gäste
    -0.67
     Sicherheits
    -0.67
    ไหม
    -0.67
    POSITIVE LOGITS
    Feat
    1.05
     feat
    1.02
    feat
    1.01
     prestige
    0.99
     Feat
    0.93
    feats
    0.91
     feats
    0.90
     spher
    0.81
     Prestige
    0.80
     collectivités
    0.78
    Activations Density 0.024%

    No Known Activations