© 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. 36179
    Prev
    Next
    INDEX
    Explanations

    expecting something to happen

    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
     可愛
    0.46
     東京都
    0.43
     dikdört
    0.42
     vyš
    0.41
     resizing
    0.41
     {}>
    0.41
     primjer
    0.40
    лення
    0.39
    piry
    0.39
     þ
    0.39
    POSITIVE LOGITS
    affected
    0.46
    ere
    0.46
    的环境
    0.45
     asshole
    0.44
    ok
    0.43
     panicked
    0.43
     靴
    0.42
    n
    0.41
    ay
    0.41
    egna
    0.41
    Activations Density 0.002%

    No Known Activations