© 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. 138367
    Prev
    Next
    INDEX
    Explanations

    Shenandoah

    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
    5
    0.70
    8
    0.70
    ྦ
    0.67
    6
    0.65
    7
    0.63
    ようになって
    0.63
     eaten
    0.59
    <strong>
    0.59
     pięk
    0.58
     flattened
    0.56
    POSITIVE LOGITS
     Mecklenburg
    0.73
    ق
    0.71
    on
    0.71
    ichés
    0.71
    üm
    0.70
    ták
    0.70
    atán
    0.69
    нами
    0.66
    führt
    0.66
    ওসি
    0.66
    Activations Density 0.000%

    No Known Activations