© 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. 50111
    Prev
    Next
    INDEX
    Explanations

    in beautiful USA Mayo

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

    patch merging

    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
    н
    0.62
    ς
    0.54
    น
    0.50
    Tiene
    0.50
     имеет
    0.49
     бес
    0.49
     номина
    0.49
    ста
    0.49
     intervención
    0.49
    mq
    0.48
    POSITIVE LOGITS
     Concise
    0.47
     Therapist
    0.45
     eigenvector
    0.45
     cinematic
    0.43
    梔
    0.43
     Θ
    0.42
     bullshit
    0.42
     complacency
    0.42
     dictionary
    0.41
     Lorentzian
    0.41
    Activations Density 0.000%

    No Known Activations