© 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. 143712
    Prev
    Next
    INDEX
    Explanations

    non-english characters

    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
     Ludwig
    0.47
    m
    0.46
    j
    0.46
     Lud
    0.44
     Hot
    0.44
     Barbados
    0.43
    cheduled
    0.43
     loyal
    0.42
     Aug
    0.41
     Ony
    0.40
    POSITIVE LOGITS
    ો
    0.49
     شك
    0.47
     unst
    0.46
     أك
    0.45
     coalesce
    0.43
     çift
    0.42
    ând
    0.42
     ઝ
    0.42
    ང
    0.42
    ки
    0.42
    Activations Density 0.004%

    No Known Activations