© 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. 109919
    Prev
    Next
    INDEX
    Explanations

    source code license

    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
     Emin
    -0.78
    مة
    -0.75
     GW
    -0.73
     შ
    -0.70
    コマ
    -0.65
     workshops
    -0.65
    penes
    -0.65
    lij
    -0.64
     Wol
    -0.64
     विश
    -0.64
    POSITIVE LOGITS
    剪
    0.73
    preorder
    0.72
     Svizzera
    0.71
     wszyscy
    0.70
     反
    0.70
     dokumen
    0.69
     SILVA
    0.67
     oplossing
    0.67
     illustratie
    0.67
     Backman
    0.67
    Activations Density 0.038%

    No Known Activations