© 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. 196559
    Prev
    Next
    INDEX
    Explanations

    setting for then room

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

    close enough

    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
    ambilan
    0.59
    ený
    0.50
     unrelenting
    0.48
     الخير
    0.47
    🇳
    0.46
    فين
    0.46
    プーン
    0.46
     potř
    0.45
     unwavering
    0.45
    였습니다
    0.45
    POSITIVE LOGITS
     visualize
    0.50
     kun
    0.50
     чемпионаты
    0.50
     vis
    0.49
     muzzle
    0.47
    ɭ
    0.46
     yax
    0.44
    WebApplication
    0.44
     tu
    0.43
     ശിഷ്യ
    0.43
    Activations Density 0.000%

    No Known Activations