Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 119880
    Prev
    Next
    INDEX
    Explanations

    available state or negation

    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
     search
    0.45
     zoeken
    0.43
    щение
    0.42
    gif
    0.42
    search
    0.41
     suchen
    0.40
     recentemente
    0.39
    捐
    0.39
    owana
    0.39
    screenshots
    0.39
    POSITIVE LOGITS
     disponible
    0.45
     disponível
    0.44
    Available
    0.42
     available
    0.41
     AVAILABLE
    0.41
    經驗
    0.41
    Table
    0.41
     Available
    0.41
     COLOR
    0.39
     discipl
    0.39
    Activations Density 0.000%

    No Known Activations