© 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. 16-GEMMASCOPE-2-RES-262K
    7. 103655
    Prev
    Next
    INDEX
    Explanations

    ceiling light, damage, and fans

    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_16_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
     mansion
    0.65
     न्यायालया
    0.63
     tòa
    0.57
    0.56
     બનાવ
    0.55
    ylsulfanyl
    0.54
    垲
    0.54
     townhouse
    0.54
     petition
    0.53
    ificada
    0.52
    POSITIVE LOGITS
    IN
    0.70
    L
    0.64
    ಮ
    0.61
    SCO
    0.60
    MET
    0.59
    RI
    0.58
    RE
    0.57
    MO
    0.57
    Sha
    0.57
    ch
    0.56
    Activations Density 0.001%

    No Known Activations