© 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. 118831
    Prev
    Next
    INDEX
    Explanations

    U.S. Pat. No

    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
     Sew
    -0.72
    changer
    -0.72
    <0x8D>
    -0.68
     Pleasure
    -0.67
    System
    -0.67
    -0.65
     Polym
    -0.65
     lacivert
    -0.65
     Marken
    -0.65
    ển
    -0.65
    POSITIVE LOGITS
    eef
    0.74
    ceira
    0.68
     dojo
    0.67
    gsSP
    0.65
     시간
    0.65
     트
    0.65
     circunstancia
    0.64
     Cómo
    0.63
    îtra
    0.63
    oodoo
    0.63
    Activations Density 0.046%

    No Known Activations