© 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. 138046
    Prev
    Next
    INDEX
    Explanations

    Python package metadata and build systems

    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
    en
    0.76
    é
    0.65
    де
    0.60
     Alpes
    0.60
    ب
    0.60
     правом
    0.59
    m
    0.57
    煸
    0.57
    l
    0.57
    mén
    0.55
    POSITIVE LOGITS
     muchas
    0.59
     photosynthetic
    0.58
     colspan
    0.57
     bike
    0.57
     photosynthesis
    0.57
    麼
    0.56
     ketchup
    0.56
     कनेक्टिविटी
    0.56
    νος
    0.55
    ective
    0.55
    Activations Density 0.002%

    No Known Activations