© 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. 27192
    Prev
    Next
    INDEX
    Explanations

    holy + noun (place, thing, time)

    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
    在
    1.41
     in
    1.41
    も
    1.10
     في
    0.98
    도
    0.93
    ও
    0.89
    も含
    0.89
    もら
    0.89
    を採用
    0.87
    是
    0.86
    POSITIVE LOGITS
    age
    0.98
    ang
    0.97
    res
    0.93
    aim
    0.88
    ati
    0.87
    ant
    0.86
    og
    0.86
    ach
    0.85
    ailing
    0.84
    itt
    0.82
    Activations Density 0.003%

    No Known Activations