© 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. 168888
    Prev
    Next
    INDEX
    Explanations

    scoff, height, assess

    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
    0
    0.46
     teilweise
    0.40
     وكانت
    0.40
    two
    0.39
    ي
    0.39
     a
    0.39
    ella
    0.39
     two
    0.39
    elle
    0.38
    ízo
    0.38
    POSITIVE LOGITS
    终止
    0.49
     නිෂ්
    0.48
    罌
    0.46
    Coluna
    0.45
    蛯
    0.45
    আমর
    0.43
    颉
    0.43
    AppData
    0.42
    getProperty
    0.42
     AppCompatTheme
    0.42
    Activations Density 0.016%

    No Known Activations