Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 3179
    Prev
    Next
    INDEX
    Explanations

    special characters and structure words

    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_31_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
    运营
    0.46
     আন্দোলনে
    0.43
    मर्द
    0.43
    మే
    0.43
    лоба
    0.43
    区块链
    0.43
    捛
    0.43
     व्हाउचर
    0.42
    탰
    0.42
    投資
    0.41
    POSITIVE LOGITS
     the
    0.56
    :
    0.48
     The
    0.47
     what
    0.47
     you
    0.46
     oral
    0.46
     choir
    0.46
     canned
    0.46
    .
    0.43
     how
    0.43
    Activations Density 0.002%

    No Known Activations