© 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. 200095
    Prev
    Next
    INDEX
    Explanations

    multiples of 4 and 6

    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
    垷
    0.51
    כת
    0.49
    ⸨
    0.49
     तहसीलदार
    0.48
    遺跡
    0.48
     കൃ
    0.48
    ันทร์
    0.47
    ㊗
    0.47
     ಜೊ
    0.46
     accuses
    0.46
    POSITIVE LOGITS
    3
    0.50
    in
    0.49
    5
    0.46
    4
    0.46
    年
    0.44
    ermost
    0.44
     SC
    0.44
     V
    0.43
    bp
    0.43
     Don
    0.43
    Activations Density 0.000%

    No Known Activations