© 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. 33996
    Prev
    Next
    INDEX
    Explanations

    numbered questions or prompts

    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
    ⬅
    0.36
     HomeScreen
    0.36
    লির
    0.36
     handout
    0.36
     connectors
    0.35
     quadrants
    0.35
    ಲೂ
    0.35
    oflav
    0.35
     গায়ে
    0.35
    floating
    0.35
    POSITIVE LOGITS
    әне
    0.50
     déclare
    0.38
     følgende
    0.38
    cca
    0.37
    രാജ
    0.37
    赘
    0.36
    FK
    0.36
     égard
    0.36
    Cet
    0.36
     Leverkusen
    0.35
    Activations Density 0.000%

    No Known Activations