© 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. 118884
    Prev
    Next
    INDEX
    Explanations

    scaling factors (2x, 3x) and filenames

    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
     союз
    -0.79
    wijk
    -0.77
    riger
    -0.74
    Alec
    -0.74
     Lean
    -0.71
    aco
    -0.70
    amini
    -0.68
    🥓
    -0.68
    ικα
    -0.67
    Tidal
    -0.66
    POSITIVE LOGITS
    Пет
    0.65
    valente
    0.63
    RequestBuilder
    0.62
    maier
    0.61
    客户
    0.59
    хия
    0.59
     valuta
    0.58
    パン
    0.58
     ステージ
    0.57
     terdapat
    0.57
    Activations Density 0.046%

    No Known Activations