© 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. 220300
    Prev
    Next
    INDEX
    Explanations

    of the year

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

    polite refusal or irritated response

    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
     മാത്രമല്ല
    0.48
     растение
    0.47
    ﮔ
    0.46
    ЛЯ
    0.46
     بق
    0.45
     proyecto
    0.43
    Lemma
    0.43
     районов
    0.42
     comentário
    0.42
    گ
    0.42
    POSITIVE LOGITS
    updating
    0.46
     Immun
    0.43
     immunization
    0.43
     Scotch
    0.42
    scotch
    0.42
     ผ่าน
    0.41
     hauling
    0.41
    micron
    0.41
     USAF
    0.41
     તેની
    0.40
    Activations Density 0.001%

    No Known Activations