© 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. 184635
    Prev
    Next
    INDEX
    Explanations

    spatial configurations

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

    projects, instructions, and specific names

    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
    ご
    0.47
     granting
    0.46
    の大
    0.45
     Tuesdays
    0.45
     radionu
    0.44
     över
    0.43
     maxit
    0.43
     sovr
    0.43
     brews
    0.43
     jus
    0.43
    POSITIVE LOGITS
    akuan
    0.47
    க்கும்
    0.46
    犁
    0.46
     አካ
    0.45
    ম্প
    0.44
    פים
    0.44
    Accessible
    0.43
    ס
    0.42
    famil
    0.42
    ப்பட்டது
    0.41
    Activations Density 0.000%

    No Known Activations