© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 6701
    Prev
    Next
    INDEX
    Explanations

    movement and expression

    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
    𒂗
    0.44
    grado
    0.41
    叁
    0.41
     reckoned
    0.39
    ahrer
    0.39
    arasi
    0.39
     rechten
    0.38
    ">//
    0.38
     concurred
    0.38
     Buenas
    0.37
    POSITIVE LOGITS
     portions
    0.39
     rigidly
    0.37
     keç
    0.37
     painfully
    0.36
     monstros
    0.36
     hand
    0.36
    yg
    0.35
    רוי
    0.35
    ições
    0.34
     monstrous
    0.34
    Activations Density 0.000%

    No Known Activations