© 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. 40-GEMMASCOPE-2-RES-262K
    7. 27850
    Prev
    Next
    INDEX
    Explanations

    user access

    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_40_width_262k_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
    airie
    0.44
    wbr
    0.43
     udal
    0.40
    袤
    0.38
    bands
    0.37
    ارتی
    0.37
    泞
    0.37
    uere
    0.37
    薔
    0.37
    bamos
    0.37
    POSITIVE LOGITS
    rient
    0.39
     Jelly
    0.38
    对手
    0.38
     lax
    0.37
     sarcom
    0.36
     loadAnimation
    0.36
     Tasting
    0.36
     flavour
    0.36
     Expert
    0.36
    ryt
    0.36
    Activations Density 0.000%

    No Known Activations