© 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. 16-GEMMASCOPE-2-RES-262K
    7. 17471
    Prev
    Next
    INDEX
    Explanations

    dropdown menu or field

    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_16_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
    ;
    1.00
     )}$
    0.70
     تساوي
    0.67
     frictionless
    0.67
    كى
    0.65
     których
    0.65
     delici
    0.65
     reducible
    0.63
     decorated
    0.61
    كي
    0.61
    POSITIVE LOGITS
     dropdown
    0.95
    and
    0.89
    ت
    0.88
    dropdown
    0.84
    at
    0.79
    à
    0.78
    et
    0.75
    ות
    0.75
    as
    0.74
    ж
    0.74
    Activations Density 0.012%

    No Known Activations