© 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. 174881
    Prev
    Next
    INDEX
    Explanations

    used to save

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

    React Strict Mode

    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
     ভয়ে
    0.44
    最
    0.42
     seguente
    0.42
    CRYPT
    0.41
    外出
    0.41
    第四
    0.41
     adherent
    0.41
    ored
    0.41
    ることが
    0.40
    BOLD
    0.40
    POSITIVE LOGITS
     País
    0.57
     Alfredo
    0.52
     Oficina
    0.52
     সাম্প্রতিক
    0.50
     Kyushu
    0.50
     Phương
    0.49
    觑
    0.49
     rRNA
    0.49
     Ethiopia
    0.48
     República
    0.48
    Activations Density 0.000%

    No Known Activations