© 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. 183860
    Prev
    Next
    INDEX
    Explanations

    biofuel, sea lion, LaTeX

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

    large, risk, trustee, SAF

    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
     recounts
    0.54
    歪
    0.48
     Noir
    0.45
     pais
    0.44
     Edgar
    0.44
     Razer
    0.44
     Warhammer
    0.44
     Tarot
    0.44
     Marcell
    0.44
     hedon
    0.44
    POSITIVE LOGITS
    t
    0.54
    u
    0.54
    aad
    0.52
    p
    0.50
    i
    0.49
    c
    0.46
    ле
    0.46
    it
    0.44
    au
    0.43
    birth
    0.42
    Activations Density 0.001%

    No Known Activations