© 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. 63020
    Prev
    Next
    INDEX
    Explanations

    char pointer declaration

    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
    Ár
    -0.79
     každ
    -0.76
    signature
    -0.74
    urz
    -0.70
     Arno
    -0.69
     Cabello
    -0.68
    asche
    -0.68
    ټ
    -0.68
    Fiz
    -0.67
    Reliability
    -0.67
    POSITIVE LOGITS
    ἵ
    0.85
     Serena
    0.69
    Ча
    0.68
     zijne
    0.67
     Ча
    0.67
    łgor
    0.66
    ые
    0.66
    his
    0.66
    findall
    0.65
    His
    0.65
    Activations Density 0.023%

    No Known Activations