© 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. 23964
    Prev
    Next
    INDEX
    Explanations

    numbers, symbols, foreign words

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

    "you" or "me"

    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
     WHILE
    0.44
     Rog
    0.44
    ллер
    0.44
     NEGLIGENCE
    0.44
     Drexel
    0.44
     WILL
    0.43
     Rutgers
    0.43
     //
    0.43
     THEY
    0.43
     tortor
    0.43
    POSITIVE LOGITS
    ین
    0.59
     économiques
    0.49
    モ
    0.47
     legislação
    0.46
    མ
    0.46
    შ
    0.45
    cció
    0.45
     estadounid
    0.44
    ম্মদ
    0.44
    ض
    0.44
    Activations Density 0.000%

    No Known Activations