© 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. 110956
    Prev
    Next
    INDEX
    Explanations

    phrases of knowing or believing

    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
    ,
    0.57
    :
    0.44
    **
    0.44
     **
    0.44
    **,
    0.43
     ref
    0.42
    :**
    0.42
     will
    0.41
     tail
    0.40
     prolong
    0.40
    POSITIVE LOGITS
    Ꮂ
    0.45
     aussitôt
    0.44
    الش
    0.41
    쌌
    0.41
    茟
    0.41
    ২৩
    0.40
     entièrement
    0.40
    ڽ
    0.40
    😬
    0.39
     naturels
    0.39
    Activations Density 0.019%

    No Known Activations