© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 16152
    Prev
    Next
    INDEX
    Explanations

    action verbs followed by dashes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <0x80>
    0.61
    f
    0.58
    ik
    0.57
    <
    0.55
    reserved
    0.53
     attracted
    0.53
     in
    0.52
    constructed
    0.51
    4
    0.51
     attacked
    0.51
    POSITIVE LOGITS
    able
    0.62
    וי
    0.58
    는
    0.58
    ﻚ
    0.56
    िंग
    0.55
     '">'
    0.54
    וס
    0.52
     компонентов
    0.51
     लाभार्थियों
    0.51
    ımızın
    0.50
    Activations Density 0.068%

    No Known Activations