© 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. 21726
    Prev
    Next
    INDEX
    Explanations

    shipping or foreign locales

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

    resources and information

    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
     bolo
    0.50
     morales
    0.50
     start
    0.50
     toothpaste
    0.49
     sinus
    0.48
    🛳
    0.48
     pedicure
    0.48
     bucket
    0.47
     tattoo
    0.47
     bridge
    0.47
    POSITIVE LOGITS
    bieter
    0.52
    资源
    0.52
     Obwohl
    0.49
    主管部门
    0.48
     সহায়তা
    0.47
     بازیکن
    0.47
    㒵
    0.47
     Resource
    0.47
    委员
    0.47
     صارفین
    0.47
    Activations Density 0.000%

    No Known Activations