© 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. 26666
    Prev
    Next
    INDEX
    Explanations

    you will find

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

    text structure markers

    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
     eingesetzt
    0.39
    ﾓ
    0.38
     اتش
    0.37
     Ferreira
    0.36
    แต
    0.36
    Bueno
    0.35
    😷
    0.35
    <unused2121>
    0.35
    প্রসঙ্গত
    0.35
    ंबा
    0.34
    POSITIVE LOGITS
    header
    0.42
     চারপাশে
    0.42
    coil
    0.41
     soltanto
    0.40
     Ци
    0.40
    course
    0.39
    tained
    0.39
    cors
    0.39
     მხოლოდ
    0.38
    ár
    0.38
    Activations Density 0.044%

    No Known Activations