© 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. 9900
    Prev
    Next
    INDEX
    Explanations

    pain, security, research, sharp

    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
     印
    0.50
     ज्ञात
    0.47
    뤽
    0.47
    ᐸ
    0.46
     máxima
    0.46
    フィ
    0.46
    INEN
    0.46
     피
    0.46
    치
    0.46
     ಬಿಯ
    0.46
    POSITIVE LOGITS
    ataan
    0.47
    ov
    0.45
     muzzle
    0.45
    ay
    0.44
    m
    0.44
    ve
    0.44
    og
    0.44
    ภัณฑ์
    0.43
    jete
    0.43
    os
    0.42
    Activations Density 0.003%

    No Known Activations