© 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. 203433
    Prev
    Next
    INDEX
    Explanations

    aggression on, years old, facilitate, uk>, ( now, is simple

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

    categories and descriptors

    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
     novedad
    0.47
    EW
    0.47
    c
    0.46
     negociación
    0.45
     implementación
    0.45
     Households
    0.43
     Feuilles
    0.43
    the
    0.42
    poses
    0.42
     esprim
    0.42
    POSITIVE LOGITS
    ⁢</
    0.49
    aik
    0.48
     leukemia
    0.48
     cheque
    0.47
     dyslex
    0.47
     kitchen
    0.45
     dyslexia
    0.44
     melanoma
    0.44
    యి
    0.43
     guitar
    0.43
    Activations Density 0.001%

    No Known Activations