© 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. 115553
    Prev
    Next
    INDEX
    Explanations

    present, thesis, reaction, reasons, own

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

    haftungsbeschränkt UG

    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
     точка
    0.50
     terminate
    0.48
     Dario
    0.45
     термина
    0.45
    埶
    0.45
    amata
    0.44
    掾
    0.44
    айл
    0.43
     професси
    0.43
     प्रमाणात
    0.43
    POSITIVE LOGITS
    回路
    0.45
    ModelAndView
    0.45
    calculation
    0.45
    たら
    0.44
     oscillators
    0.44
    bours
    0.43
    袴
    0.42
    ミング
    0.42
    radioButton
    0.42
    findAll
    0.42
    Activations Density 0.001%

    No Known Activations