© 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. 118651
    Prev
    Next
    INDEX
    Explanations

    version 2.0 or later

    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
     mostrarse
    -0.79
     getValue
    -0.71
     currentIndex
    -0.69
    peche
    -0.68
     skóry
    -0.68
     ApiResponse
    -0.66
     spinal
    -0.66
    膨
    -0.65
     youll
    -0.65
     pelear
    -0.65
    POSITIVE LOGITS
    Katz
    0.83
     Adopted
    0.77
     Katz
    0.77
    jante
    0.73
     Ionic
    0.73
    boek
    0.73
    eken
    0.70
     فرق
    0.70
     dici
    0.69
    Massa
    0.69
    Activations Density 0.063%

    No Known Activations