© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 81018
    Prev
    Next
    INDEX
    Explanations

    partner, works, increasing, rewarding

    np_acts-logits-general · gemini-2.5-flash-lite

    often, potentially, beyond, growing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    忧
    0.46
    levard
    0.46
     bram
    0.45
    ্দ্র
    0.43
    Spread
    0.42
     heartache
    0.41
    Character
    0.40
    Solved
    0.39
    BLE
    0.38
    Pointer
    0.38
    POSITIVE LOGITS
    igenous
    0.52
    遺跡
    0.50
    ಹು
    0.49
     receptors
    0.48
    =.
    0.47
     कुल
    0.47
     बताइए
    0.46
    清潔
    0.45
    ܡܪ
    0.45
     चिह्नित
    0.45
    Activations Density 0.000%

    No Known Activations