© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 14146
    Prev
    Next
    INDEX
    Explanations

    two main types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    noch
    0.52
    glow
    0.47
    裤
    0.46
    query
    0.46
    user
    0.46
    risch
    0.45
    "]},
    0.45
    lens
    0.45
    pants
    0.45
    ባቢ
    0.45
    POSITIVE LOGITS
     legno
    0.49
     but
    0.48
     siège
    0.46
     ၂
    0.46
     Inj
    0.46
     pill
    0.46
     citado
    0.46
     poderoso
    0.46
     proteção
    0.45
     séptimo
    0.45
    Activations Density 0.001%

    No Known Activations