© 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. 14997
    Prev
    Next
    INDEX
    Explanations

    requests for money

    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
     differ
    0.40
     épaisse
    0.40
     communicative
    0.39
     -
    0.39
     conical
    0.39
     Difer
    0.39
     percent
    0.38
     commissions
    0.38
     branched
    0.38
     কণ্
    0.38
    POSITIVE LOGITS
    Kill
    0.44
    规
    0.42
     النسبيه
    0.42
     Kill
    0.41
    बोर्ड
    0.41
    煂
    0.41
     disobedience
    0.41
     ಏಕೆಂದರೆ
    0.41
    呂
    0.41
    öffentlich
    0.40
    Activations Density 0.001%

    No Known Activations