© 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. 73575
    Prev
    Next
    INDEX
    Explanations

    interact with

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

    help with instructions

    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
     suffisante
    0.55
    ຂໍ້ມ
    0.52
    机会
    0.50
    财务
    0.49
     rischio
    0.48
    তায়
    0.48
    可爱
    0.48
    烫
    0.48
     ısı
    0.47
     热
    0.47
    POSITIVE LOGITS
    SEQ
    0.49
    Q
    0.45
     anthropogenic
    0.45
     functor
    0.45
     syllable
    0.45
    mathbf
    0.44
    IN
    0.43
     themed
    0.42
     sapiens
    0.41
    LF
    0.40
    Activations Density 0.000%

    No Known Activations