© 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. 120571
    Prev
    Next
    INDEX
    Explanations

    Indica, Sativa, Hybrid

    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
    et
    0.59
    k
    0.56
    stechn
    0.52
    n
    0.47
     finde
    0.47
    spe
    0.46
    flutter
    0.46
    弋
    0.46
    excellence
    0.46
    statement
    0.45
    POSITIVE LOGITS
    יר
    0.47
     eixo
    0.47
     infected
    0.47
    :
    0.47
    伸手
    0.46
     vang
    0.46
    бан
    0.45
    গ্রেস
    0.45
     EGA
    0.45
     indicar
    0.44
    Activations Density 0.000%

    No Known Activations