© 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. 16-GEMMASCOPE-2-RES-262K
    7. 103829
    Prev
    Next
    INDEX
    Explanations

    calorie, low-calorie, snacks, condiment

    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_16_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
    los
    0.55
    رین
    0.55
    lo
    0.54
    zott
    0.53
    şık
    0.53
    şti
    0.52
    ş
    0.52
    ở
    0.52
    tı
    0.52
    zł
    0.51
    POSITIVE LOGITS
     eliminated
    0.45
     также
    0.45
     Gregory
    0.45
     \
    0.45
     furry
    0.43
     emanating
    0.43
     casino
    0.43
     also
    0.42
     winged
    0.42
     on
    0.42
    Activations Density 0.000%

    No Known Activations