© 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. 20738
    Prev
    Next
    INDEX
    Explanations

    foreign characters and language

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

    While or historically

    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
    bad
    0.55
    ฟ
    0.55
    F
    0.54
     Doppio
    0.52
    ส
    0.51
    sm
    0.50
    slam
    0.50
    L
    0.49
    christian
    0.49
    image
    0.49
    POSITIVE LOGITS
     zamanda
    0.50
     reú
    0.50
     neutralize
    0.49
     юби
    0.48
     recepción
    0.47
     воспользова
    0.47
     суб
    0.46
     sfera
    0.46
     農
    0.46
     здрав
    0.45
    Activations Density 0.000%

    No Known Activations