© 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. 141980
    Prev
    Next
    INDEX
    Explanations

    Telegram messaging app

    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
    p
    1.01
    b
    0.88
    ک
    0.82
    ۵
    0.80
    ст
    0.79
    inas
    0.77
    urro
    0.76
     divergents
    0.76
    inin
    0.74
    ur
    0.73
    POSITIVE LOGITS
     Telegram
    0.78
    U
    0.75
    I
    0.75
    కు
    0.73
    ّ
    0.70
    0.70
    dır
    0.66
     výro
    0.66
    Telegram
    0.65
    R
    0.65
    Activations Density 0.002%

    No Known Activations