© 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. 48269
    Prev
    Next
    INDEX
    Explanations

    you usually, you used to

    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
    ך
    0.50
    ches
    0.48
     Generated
    0.48
    americanos
    0.48
    átiles
    0.48
    printer
    0.48
    raintree
    0.47
    Printer
    0.46
    ön
    0.46
    matched
    0.45
    POSITIVE LOGITS
    의
    0.54
     inad
    0.53
     enclose
    0.52
    త
    0.50
     hike
    0.48
     alloys
    0.47
     asylum
    0.46
     heirs
    0.45
    자
    0.45
     encode
    0.44
    Activations Density 0.001%

    No Known Activations