© 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. 4170
    Prev
    Next
    INDEX
    Explanations

    fields and practices

    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
    с
    0.62
    的
    0.56
    AR
    0.55
    کر
    0.54
    čas
    0.54
    用
    0.53
    وم
    0.53
    ので
    0.51
    我们
    0.50
    بی
    0.50
    POSITIVE LOGITS
    an
    0.83
    r
    0.65
    is
    0.63
    in
    0.61
    t
    0.60
    x
    0.59
    k
    0.56
     pigments
    0.55
     mammals
    0.54
     immortality
    0.54
    Activations Density 2.152%

    No Known Activations