© 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. 6264
    Prev
    Next
    INDEX
    Explanations

    contrasting or additional items

    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
    يت
    0.46
    }$
    0.39
     cả
    0.38
     εί
    0.38
     thiết
    0.37
    幵
    0.35
     ajuda
    0.35
     усі
    0.35
     τραγ
    0.35
     is
    0.35
    POSITIVE LOGITS
    h
    0.51
    in
    0.51
    s
    0.45
    ap
    0.44
    ia
    0.43
    d
    0.43
    p
    0.42
    o
    0.39
     (
    0.38
    ha
    0.38
    Activations Density 0.794%

    No Known Activations