© 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. 35932
    Prev
    Next
    INDEX
    Explanations

    body, score, sizes, travel

    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
    醗
    0.43
     Mg
    0.38
     Managers
    0.38
     ERROR
    0.37
     erd
    0.37
     modo
    0.36
     flask
    0.36
     Hearing
    0.36
     conlle
    0.36
    <unused10>
    0.35
    POSITIVE LOGITS
     swipes
    0.47
     malignancy
    0.44
    Ghosts
    0.43
     ghost
    0.43
     korero
    0.41
    Ghost
    0.40
    ghost
    0.40
    UI
    0.40
    notify
    0.40
    bris
    0.39
    Activations Density 0.000%

    No Known Activations