© 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. 138315
    Prev
    Next
    INDEX
    Explanations

    polyphonic, itian, ium, Arthur

    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
     រ
    0.61
    IPP
    0.57
     ruhig
    0.57
    s
    0.57
     leicht
    0.55
     كريم
    0.55
     ኢን
    0.54
     sangre
    0.53
     Villages
    0.53
     Nunca
    0.52
    POSITIVE LOGITS
    کان
    0.60
    리티
    0.59
    radial
    0.59
    蓴
    0.59
    стер
    0.59
    ناک
    0.57
     equivalently
    0.55
    ப்பத
    0.55
    рафон
    0.54
    чини
    0.54
    Activations Density 0.000%

    No Known Activations