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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 110531
    Prev
    Next
    INDEX
    Explanations

    FOR purpose, accordance, qualified

    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
    ச
    -0.88
     stationnement
    -0.82
     generously
    -0.79
     Obj
    -0.76
    บ
    -0.76
     both
    -0.75
    包
    -0.75
    碼
    -0.74
     Kuru
    -0.74
     tė
    -0.73
    POSITIVE LOGITS
    expects
    0.94
     Funcion
    0.85
    recursive
    0.81
    rhyth
    0.80
     ohne
    0.79
    ಂದು
    0.77
     children
    0.77
     or
    0.76
    yte
    0.76
     каких
    0.75
    Activations Density 0.031%

    No Known Activations