© 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. 40-GEMMASCOPE-2-RES-262K
    7. 120316
    Prev
    Next
    INDEX
    Explanations

    electrical, metal, sound, equipment

    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_40_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
    农业
    0.42
    ธอ
    0.41
    جمة
    0.41
    渠
    0.39
    Agriculture
    0.39
     agriculture
    0.38
    verno
    0.38
    cije
    0.38
     pure
    0.37
     Agriculture
    0.37
    POSITIVE LOGITS
    棄
    0.42
    imageList
    0.42
    Produkt
    0.41
     SIGN
    0.40
    Forbidden
    0.40
    Lud
    0.39
     машин
    0.39
     connect
    0.39
    CONTAIN
    0.39
     Фурга
    0.38
    Activations Density 0.006%

    No Known Activations