© 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. 8360
    Prev
    Next
    INDEX
    Explanations

    available/occurrences for

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

    existence and purpose

    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
     번째
    0.20
    '
    0.19
    ylmethyl
    0.18
     andRow
    0.17
     大き
    0.17
     vibrates
    0.17
     و
    0.17
     শ্
    0.17
     infrared
    0.17
    ৫
    0.17
    POSITIVE LOGITS
     для
    0.31
    для
    0.24
     pentru
    0.23
     untuk
    0.22
     για
    0.21
     каждому
    0.21
     voor
    0.21
     لدى
    0.21
     لهذه
    0.20
    Для
    0.20
    Activations Density 0.565%

    No Known Activations