© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9336
    Prev
    Next
    INDEX
    Explanations

    computing services

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

    system service commands

    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_40_width_16k_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
     DAC
    0.42
    週間
    0.42
     달
    0.42
    DAL
    0.42
    לח
    0.41
     ライト
    0.40
    衆
    0.40
    沨
    0.40
     पेट
    0.39
     সমাধিতে
    0.39
    POSITIVE LOGITS
    UserService
    1.61
    userService
    1.54
     UserService
    1.52
     userService
    1.44
    サービス
    1.39
     serviço
    1.39
     service
    1.38
     hizmet
    1.36
     AuthService
    1.34
     servicio
    1.30
    Activations Density 0.045%

    No Known Activations