© 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. 17467
    Prev
    Next
    INDEX
    Explanations

    primary

    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
    ある
    1.23
    ول
    1.09
    なく
    1.05
    禕
    1.02
    ن
    0.99
    お
    0.98
     be
    0.96
    AA
    0.96
    い
    0.95
    AK
    0.91
    POSITIVE LOGITS
    u
    1.73
    ing
    1.56
    us
    1.38
    s
    1.29
    uhe
    1.21
    i
    1.16
    uq
    1.13
    ی
    1.10
    ле
    1.05
    ्स
    1.04
    Activations Density 0.015%

    No Known Activations