© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 179464
    Prev
    Next
    INDEX
    Explanations

    pickup of

    np_acts-logits-general · gemini-2.5-flash-lite

    resources and end dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     هذ
    0.53
    ína
    0.50
    íf
    0.48
    ívá
    0.46
     将
    0.45
     ง
    0.45
    irá
    0.45
    鳕
    0.44
    arians
    0.43
     रोहित
    0.43
    POSITIVE LOGITS
    ڄ
    0.49
    DER
    0.48
    恂
    0.47
    PHIL
    0.47
     veces
    0.46
    اہم
    0.46
    د
    0.46
     longiore
    0.46
    дон
    0.46
    CHEN
    0.46
    Activations Density 0.000%

    No Known Activations