© 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. 40728
    Prev
    Next
    INDEX
    Explanations

    capacitor and ethanol

    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
     tribunals
    0.90
    یه
    0.88
    زیز
    0.88
    ی
    0.86
    ettiin
    0.85
     in
    0.84
     ځای
    0.83
    ټبال
    0.82
    ⓪
    0.81
    き
    0.79
    POSITIVE LOGITS
    an
    1.48
    '
    1.15
    a
    1.13
    on
    1.08
    lad
    1.00
    et
    0.98
    na
    0.98
    ان
    0.96
    n
    0.94
    Game
    0.93
    Activations Density 0.002%

    No Known Activations