© 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. 31-GEMMASCOPE-2-RES-262K
    7. 3703
    Prev
    Next
    INDEX
    Explanations

    programming contexts

    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_31_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
     Coker
    0.48
     autent
    0.48
    酽
    0.46
     partenza
    0.44
     apresentou
    0.42
     ujian
    0.42
    珍珠
    0.42
    ່ວນ
    0.42
     School
    0.42
    धित
    0.41
    POSITIVE LOGITS
    স
    0.59
     sacked
    0.47
    feng
    0.47
     바꾸
    0.46
    s
    0.44
     deflected
    0.42
     sacking
    0.42
    ্টা
    0.42
    xgb
    0.42
    reversible
    0.42
    Activations Density 0.000%

    No Known Activations