© 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. 142158
    Prev
    Next
    INDEX
    Explanations

    clearing houses, Versalles, XIV, maya, peace, origin, bridge, sclera, synthetic

    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
    絓
    0.63
    ї
    0.62
    ಿಗಳು
    0.57
    ี
    0.57
     heralded
    0.57
    ież
    0.55
    ί
    0.55
    𓃵
    0.55
    恽
    0.55
     interstitiis
    0.55
    POSITIVE LOGITS
    :
    0.59
    ATEG
    0.56
    Aid
    0.55
    Pick
    0.55
    Arg
    0.55
    Por
    0.55
    Alert
    0.54
    Are
    0.52
    Ward
    0.52
    2
    0.52
    Activations Density 0.047%

    No Known Activations