© 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. 40-GEMMASCOPE-2-RES-262K
    7. 8035
    Prev
    Next
    INDEX
    Explanations

    names, initials

    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_40_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
    4
    0.49
    7
    0.47
    8
    0.46
    5
    0.45
    9
    0.45
    6
    0.44
    3
    0.39
    1
    0.39
    2
    0.39
    0
    0.37
    POSITIVE LOGITS
    .,"
    0.33
    asser
    0.30
    .,
    0.29
    anske
    0.29
    .},
    0.29
     proteger
    0.29
    oyeva
    0.29
    ஃப்
    0.28
    addock
    0.28
    бли
    0.28
    Activations Density 0.002%

    No Known Activations