© 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. 40833
    Prev
    Next
    INDEX
    Explanations

    competitors, content, award, start

    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
     ovog
    0.42
     żół
    0.39
    0.39
    았던
    0.38
     멋
    0.38
    Aspect
    0.37
    良かった
    0.37
    eret
    0.37
     необы
    0.36
    揊
    0.36
    POSITIVE LOGITS
     instantaneously
    0.54
     ranging
    0.52
     either
    0.49
    例えば
    0.49
     আনুগত্য
    0.48
     سواء
    0.47
     चाहे
    0.47
    譬
    0.47
     regardless
    0.46
     every
    0.46
    Activations Density 0.004%

    No Known Activations