© 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. 191926
    Prev
    Next
    INDEX
    Explanations

    decor ideas

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

    sentience and abstract concepts

    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
     estándar
    0.52
     முறையாக
    0.50
     employ
    0.47
     obey
    0.47
     पद्ध
    0.46
     alami
    0.46
    Globals
    0.45
    迟
    0.45
     minum
    0.45
    Employ
    0.44
    POSITIVE LOGITS
    だったので
    0.49
    Ɔ
    0.47
    haul
    0.45
     щоб
    0.43
    なかったので
    0.43
    ঘর
    0.42
    でしたが
    0.42
     দৌড়ে
    0.41
     کھانے
    0.41
    зо
    0.40
    Activations Density 0.001%

    No Known Activations