© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 14763
    Prev
    Next
    INDEX
    Explanations

    software dependencies and libraries

    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
     like
    0.45
     clasp
    0.44
     Git
    0.44
     utils
    0.44
     `
    0.43
     npm
    0.43
     tools
    0.42
     Google
    0.41
     conda
    0.41
     torch
    0.40
    POSITIVE LOGITS
     питання
    0.40
    㗽
    0.40
    II
    0.39
    ETIC
    0.39
     পড়িল
    0.39
    ISHING
    0.39
     EVENTS
    0.39
    정책
    0.38
    ᱙
    0.38
    ULATION
    0.38
    Activations Density 0.032%

    No Known Activations