© 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. 114483
    Prev
    Next
    INDEX
    Explanations

    foundation for, practice on, basis for, center of

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

    lists and examples

    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
     دریا
    0.43
    igail
    0.41
     Евге
    0.40
    SET
    0.40
     revista
    0.39
    செ
    0.38
     perempuan
    0.38
    🥂
    0.38
    زد
    0.38
    churn
    0.38
    POSITIVE LOGITS
     crappy
    0.53
     shitty
    0.46
    ocyte
    0.45
    nut
    0.44
     alcoved
    0.43
    格
    0.43
     ``
    0.43
     mandibular
    0.43
    effici
    0.42
     δικ
    0.42
    Activations Density 0.001%

    No Known Activations