© 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. 21751
    Prev
    Next
    INDEX
    Explanations

    linking specific preceding and succeeding words

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

    specific functions

    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
     in
    0.46
     Cle
    0.44
    cle
    0.43
    Cle
    0.43
     конструкции
    0.43
    \
    0.42
    했던
    0.41
    .)
    0.41
    Flex
    0.40
    CEL
    0.40
    POSITIVE LOGITS
    graphHead
    0.50
    tcpHeader
    0.50
    testAvg
    0.48
     স্বামীর
    0.48
    etään
    0.48
     alchemy
    0.47
    kennung
    0.47
    DataXYZ
    0.47
    zentrum
    0.46
    रेशन
    0.46
    Activations Density 0.001%

    No Known Activations