© 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. 96655
    Prev
    Next
    INDEX
    Explanations

    judgment and rewards

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

    planning, system, origin, mechanism

    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
    ครอง
    0.47
     *
    0.47
    ೋ
    0.46
     Wessex
    0.44
    ઝ
    0.43
    ཥ
    0.43
    Ī
    0.43
     Meso
    0.42
     reso
    0.42
    |$
    0.42
    POSITIVE LOGITS
     opérateurs
    0.51
     française
    0.49
     já
    0.47
    惚
    0.47
     écriv
    0.46
     obtenir
    0.46
     desiring
    0.46
     operativa
    0.45
     elkaar
    0.45
     agreeing
    0.44
    Activations Density 0.001%

    No Known Activations