© 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. 232836
    Prev
    Next
    INDEX
    Explanations

    reporting on business events

    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
    Pago
    0.57
     ಒಳ್ಳೆಯ
    0.53
    eské
    0.53
     ሃ
    0.52
     సు
    0.51
    ForgotPassword
    0.50
    Tecla
    0.50
    Induced
    0.50
    jár
    0.49
    㞖
    0.48
    POSITIVE LOGITS
     ataupun
    0.51
     multimodal
    0.46
     channels
    0.46
     waters
    0.45
     internal
    0.45
     USB
    0.45
     streams
    0.45
     cleanup
    0.44
     sediments
    0.44
    ,
    0.44
    Activations Density 0.001%

    No Known Activations