© 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. 129328
    Prev
    Next
    INDEX
    Explanations

    media training, style guide, patients, software plus

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

    * formatting

    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
     交換
    0.53
    though
    0.48
    ounded
    0.47
     虽然
    0.47
    s
    0.45
     എന്നാല്‍
    0.45
     spéciale
    0.43
     होते
    0.43
    ;
    0.42
    ateau
    0.41
    POSITIVE LOGITS
    र्डर
    0.50
    шит
    0.48
     мировой
    0.46
     microbiota
    0.45
    лежа
    0.45
    राइ
    0.44
    ರ್ಗ
    0.44
    회사
    0.44
    기로
    0.44
     cifra
    0.43
    Activations Density 0.001%

    No Known Activations