© 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. 110459
    Prev
    Next
    INDEX
    Explanations

    license text

    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
    ịnh
    -0.77
     pasukan
    -0.70
    sile
    -0.69
    OOTDTY
    -0.69
    لمانيا
    -0.68
     Sorge
    -0.67
     apabila
    -0.66
    частли
    -0.66
    Fá
    -0.65
     κυ
    -0.65
    POSITIVE LOGITS
     Kenyatta
    0.80
     понял
    0.69
     Postal
    0.69
    受信
    0.69
    年度
    0.68
    허
    0.66
     frow
    0.66
     refe
    0.65
    êu
    0.65
    ライ
    0.65
    Activations Density 0.021%

    No Known Activations