© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 110503
    Prev
    Next
    INDEX
    Explanations

    listing skills or attributes

    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
    Both
    -1.09
    Neither
    -0.93
    islav
    -0.88
     consiguiente
    -0.85
    athlon
    -0.85
    lamic
    -0.83
    CAPITULO
    -0.83
     illustratie
    -0.82
    both
    -0.82
    érable
    -0.82
    POSITIVE LOGITS
     namely
    1.14
     its
    0.82
    ㈠
    0.81
    ?,?,
    0.81
    ())
    0.80
     (
    0.79
    цвет
    0.79
    ①
    0.79
    cay
    0.79
     크
    0.79
    Activations Density 0.101%

    No Known Activations