© 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. 31847
    Prev
    Next
    INDEX
    Explanations

    sql insert into

    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
     시
    0.42
    淳
    0.38
     revolved
    0.38
    agg
    0.36
    ifix
    0.36
    csv
    0.36
    sq
    0.35
    efore
    0.34
     қ
    0.34
    ších
    0.34
    POSITIVE LOGITS
     ignore
    0.56
     ignoring
    0.50
     ignores
    0.47
     Ignore
    0.46
    Ignore
    0.45
     ignored
    0.45
    無視
    0.44
     IG
    0.43
     shout
    0.43
    ignore
    0.43
    Activations Density 0.002%

    No Known Activations