© 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. 32919
    Prev
    Next
    INDEX
    Explanations

    academic texts

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

    outlining structure and logic

    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
    Oper
    0.43
     матч
    0.42
     एमसी
    0.40
     ಎರಡು
    0.39
    િંગ
    0.39
    MMC
    0.39
    ❼
    0.39
     Первый
    0.39
     Espí
    0.38
     lúc
    0.38
    POSITIVE LOGITS
     않아
    0.46
    ambarkan
    0.45
    肃
    0.45
     कह
    0.44
    ArgsEnv
    0.44
    해
    0.44
    䄳
    0.43
    觉得
    0.43
    exploration
    0.43
    不死
    0.43
    Activations Density 0.001%

    No Known Activations