© 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. 26826
    Prev
    Next
    INDEX
    Explanations

    academic url structure

    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
    ↵↵
    0.38
     Bry
    0.36
    ensure
    0.36
     Narrow
    0.36
     MacL
    0.35
    ев
    0.35
     vic
    0.35
    ্লিকেশন
    0.34
     Using
    0.34
    NORE
    0.34
    POSITIVE LOGITS
     финан
    0.40
    pInBuffer
    0.39
    ၅
    0.38
    ższ
    0.38
    ၃
    0.36
     pissed
    0.35
    諗
    0.35
    $.)
    0.35
     ज़रूरत
    0.35
    旕
    0.35
    Activations Density 0.002%

    No Known Activations