© 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. 80029
    Prev
    Next
    INDEX
    Explanations

    skills that, Perry utilized, News writer

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

    equipment, requests, activity, preventing acts

    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
    patx
    0.51
     considerare
    0.47
     чемпион
    0.46
     характеристи
    0.46
    贔
    0.45
     使っ
    0.45
    pric
    0.45
    範
    0.44
    ndvi
    0.44
     椅
    0.43
    POSITIVE LOGITS
    炁
    0.53
     Physician
    0.50
     Ultrasound
    0.50
     Healing
    0.49
     Audible
    0.48
     Laser
    0.48
     Earth
    0.47
     CEO
    0.47
     Reiki
    0.47
     Coyote
    0.46
    Activations Density 0.000%

    No Known Activations