© 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. 248320
    Prev
    Next
    INDEX
    Explanations

    grants, technology, Whistler, Fame, poems, sq, Dreams, induction

    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
     obscures
    0.51
    oxa
    0.48
     cached
    0.47
    ()/
    0.47
    uate
    0.45
    arik
    0.45
     invaded
    0.45
     murmured
    0.45
    噤
    0.44
    opa
    0.44
    POSITIVE LOGITS
     mínimo
    0.45
     supplémentaire
    0.44
     кожен
    0.43
    habilitation
    0.43
    STEIN
    0.42
     mandatory
    0.42
     إس
    0.41
    плом
    0.41
    postos
    0.41
    getParameter
    0.40
    Activations Density 0.000%

    No Known Activations