© 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. 16-GEMMASCOPE-2-RES-262K
    7. 3210
    Prev
    Next
    INDEX
    Explanations

    names and places

    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_16_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
    t
    1.20
    1
    1.17
    v
    1.12
    es
    1.08
    an
    1.03
    l
    1.03
    s
    1.00
    u
    1.00
    b
    0.98
    as
    0.96
    POSITIVE LOGITS
     в
    0.99
    ции
    0.84
     de
    0.79
    ও
    0.77
     σε
    0.77
    も
    0.75
     և
    0.71
     can
    0.70
     في
    0.70
    に
    0.68
    Activations Density 0.070%

    No Known Activations