© 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. 45942
    Prev
    Next
    INDEX
    Explanations

    I want

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

    multilingual concepts

    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
    既に
    0.57
    5
    0.50
    すでに
    0.49
     이미
    0.47
    4
    0.46
    6
    0.46
    St
    0.45
    が高
    0.45
    Aust
    0.44
    త్ప
    0.43
    POSITIVE LOGITS
     vengan
    0.55
     razón
    0.51
     littérature
    0.47
     şey
    0.46
     oamen
    0.46
     fileprivate
    0.46
     alimentación
    0.46
     assh
    0.45
     colère
    0.45
     dám
    0.45
    Activations Density 0.000%

    No Known Activations