© 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. 109660
    Prev
    Next
    INDEX
    Explanations

    xml processing instruction version

    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
    ricio
    -0.75
    struktur
    -0.72
    StartTag
    -0.69
    🌉
    -0.69
     reconnaît
    -0.68
    habilitar
    -0.67
     тела
    -0.67
    mleri
    -0.67
    qx
    -0.66
     physically
    -0.66
    POSITIVE LOGITS
     node
    1.03
     Piet
    0.89
    Doc
    0.87
    newNode
    0.86
    node
    0.86
    SIT
    0.78
    Piet
    0.77
    ﻃ
    0.76
     newNode
    0.75
     Pete
    0.74
    Activations Density 0.073%

    No Known Activations