© 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. 64895
    Prev
    Next
    INDEX
    Explanations

    welcoming hospitality

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

    not strictly, not simply

    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
    ל
    0.50
    ؟
    0.46
    לב
    0.45
    ם
    0.45
    რ
    0.43
     ג
    0.43
    ուն
    0.43
    猶
    0.43
     פ
    0.42
     ت
    0.42
    POSITIVE LOGITS
    效率
    0.53
     efficiency
    0.50
     compared
    0.45
     representatives
    0.45
     undoubtedly
    0.43
    心地
    0.43
     deviceInfo
    0.43
     effiz
    0.43
     নিঃসন্দেহে
    0.42
     aceptación
    0.42
    Activations Density 0.000%

    No Known Activations