© 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. 109959
    Prev
    Next
    INDEX
    Explanations

    predictability for generations

    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
    yre
    0.57
    finex
    0.54
    poque
    0.53
    gard
    0.52
    furter
    0.50
    garakan
    0.50
    ევე
    0.50
    𒄑
    0.50
    yim
    0.49
    år
    0.49
    POSITIVE LOGITS
     probably
    0.48
     {\
    0.48
     all
    0.47
     trọng
    0.47
    4
    0.47
    5
    0.46
     aggressive
    0.46
     priority
    0.45
     reproducibility
    0.45
     other
    0.45
    Activations Density 0.006%

    No Known Activations