© 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. 5342
    Prev
    Next
    INDEX
    Explanations

    originating from

    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
    姩
    0.50
     예술
    0.47
    尼亚
    0.46
     організа
    0.46
     વોર્
    0.46
    Tourist
    0.45
     террито
    0.44
    нула
    0.44
    蝣
    0.44
    चाकी
    0.44
    POSITIVE LOGITS
    <h2>
    0.47
     Con
    0.47
     H
    0.46
    ac
    0.45
     Das
    0.45
    ata
    0.45
     Cl
    0.44
    doc
    0.44
     Doc
    0.44
    6
    0.43
    Activations Density 0.000%

    No Known Activations