© 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. 50511
    Prev
    Next
    INDEX
    Explanations

    variations and specific follow-ups

    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
    <$
    0.50
     refineries
    0.47
     مست
    0.47
     guardians
    0.46
    าน
    0.45
     الب
    0.45
     clinics
    0.44
     العالمين
    0.43
    銜
    0.43
     dissipated
    0.43
    POSITIVE LOGITS
     Chord
    0.51
    리즈
    0.49
    Li
    0.49
    গ
    0.49
     Codex
    0.48
     Moment
    0.46
     Peaks
    0.46
     También
    0.46
     tê
    0.46
    KAT
    0.46
    Activations Density 0.000%

    No Known Activations