© 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. 71210
    Prev
    Next
    INDEX
    Explanations

    technical instructions, programming, multilingual

    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
    nue
    0.47
    perse
    0.43
    you
    0.42
    t
    0.42
    nuevo
    0.41
    future
    0.41
    vay
    0.41
    to
    0.41
    sous
    0.40
    颞
    0.39
    POSITIVE LOGITS
     tudi
    0.48
     Switzerland
    0.47
     छत्तीसगढ़
    0.46
     rozwiązania
    0.45
     recid
    0.45
     Dynam
    0.44
    ła
    0.44
    商品は
    0.44
     pilotes
    0.43
     maritime
    0.43
    Activations Density 0.002%

    No Known Activations