© 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. 143669
    Prev
    Next
    INDEX
    Explanations

    foreign language text

    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
    )}_{
    0.44
     tea
    0.42
    ானா
    0.41
    acola
    0.41
     todas
    0.41
     ث
    0.40
     abges
    0.40
    saus
    0.40
     fecha
    0.39
    )}(
    0.39
    POSITIVE LOGITS
     windshield
    0.46
     Nürnberg
    0.46
     край
    0.45
    ದಿ
    0.45
     экспер
    0.44
     जानकार
    0.44
     прежде
    0.44
     الصفحه
    0.44
     главным
    0.43
     रामपुर
    0.43
    Activations Density 0.000%

    No Known Activations