© 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. 77575
    Prev
    Next
    INDEX
    Explanations

    locations and sources

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

    https://

    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
    How
    0.50
    THE
    0.48
    The
    0.45
    you
    0.43
    Ε
    0.43
    Alabama
    0.42
    not
    0.42
    Pro
    0.41
    그리고
    0.40
    YOU
    0.40
    POSITIVE LOGITS
     jogadores
    0.50
     verkrij
    0.48
     tetrahedron
    0.47
     jogador
    0.46
     軽量
    0.46
     tahmin
    0.45
    ಂದರೆ
    0.44
     AsRef
    0.44
     leps
    0.43
     =>{
    0.43
    Activations Density 0.001%

    No Known Activations