© 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. 10962
    Prev
    Next
    INDEX
    Explanations

    code or lists

    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
    俎
    0.40
    ദ്ധി
    0.39
     nouns
    0.36
    必要な
    0.36
    மனித
    0.35
    SOUND
    0.35
    ීම
    0.35
     presenceData
    0.35
    ற்ச
    0.34
    枠
    0.34
    POSITIVE LOGITS
     and
    0.47
    ↵↵
    0.46
    ↵
    0.45
     কিংবা
    0.41
    onas
    0.41
    and
    0.40
    u
    0.40
     অথবা
    0.39
     Similarly
    0.39
    m
    0.39
    Activations Density 0.077%

    No Known Activations