© 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-262K
    7. 135556
    Prev
    Next
    INDEX
    Explanations

    kidney

    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_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
     combustibles
    0.50
     largement
    0.47
     trá
    0.47
     virtues
    0.44
     quinze
    0.44
    ጭ
    0.43
    FOR
    0.43
    Н
    0.42
    Ј
    0.42
     malice
    0.41
    POSITIVE LOGITS
     Logout
    0.46
     Carpenter
    0.45
     ParkingLot
    0.45
     LoginForm
    0.44
     Jour
    0.44
     Curran
    0.44
     Save
    0.44
     Tuna
    0.43
     Mary
    0.43
     Zing
    0.43
    Activations Density 0.002%

    No Known Activations