© 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. 31-GEMMASCOPE-2-RES-262K
    7. 25210
    Prev
    Next
    INDEX
    Explanations

    depends on what you mean

    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
     бед
    0.55
    const
    0.43
    ábbi
    0.42
    <0x88>
    0.40
    াচিত
    0.39
    height
    0.39
    лия
    0.38
    Imm
    0.37
    axis
    0.37
    <0x0D>
    0.36
    POSITIVE LOGITS
     doesn
    0.54
     desconoc
    0.54
     postérieure
    0.48
    बॉ
    0.46
    ल्याण
    0.46
     Transforms
    0.46
    巫
    0.46
     TRAN
    0.45
     confuses
    0.45
    䂙
    0.45
    Activations Density 0.001%

    No Known Activations