© 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. 20865
    Prev
    Next
    INDEX
    Explanations

    remarkable, remarkably

    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
    পদের
    0.48
     kilómetros
    0.44
    <unused1108>
    0.43
     ẞ
    0.43
     depiction
    0.43
     効果
    0.42
     vattum
    0.42
     巻
    0.42
    秭
    0.42
     DESCRIPTION
    0.41
    POSITIVE LOGITS
     remark
    0.71
     remarks
    0.70
    Remark
    0.69
    remark
    0.67
     Remark
    0.65
     Remarks
    0.60
    Remarks
    0.55
    备注
    0.54
    Rem
    0.54
    remarks
    0.51
    Activations Density 0.002%

    No Known Activations