© 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. 15502
    Prev
    Next
    INDEX
    Explanations

    places, people, and things

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

    directions and 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
    correo
    0.41
     ትንሽ
    0.39
    qrcode
    0.38
    潁
    0.38
     ኮ
    0.38
     स्त्रीलिंग
    0.38
     ખૂબ
    0.37
    ClF
    0.37
     मुताब
    0.36
     אַ
    0.36
    POSITIVE LOGITS
    κτή
    0.39
    ",
    0.38
    拥有
    0.37
    тельством
    0.37
    тона
    0.36
     posiada
    0.36
    形で
    0.36
     maqu
    0.35
    μάτων
    0.34
    化
    0.34
    Activations Density 0.214%

    No Known Activations