© 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. 107644
    Prev
    Next
    INDEX
    Explanations

    foundation of, target is, home, locks

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

    simulation creation code

    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
    に対
    0.54
     ='
    0.53
     кам
    0.52
     часу
    0.52
     délais
    0.52
     ката
    0.51
     relentlessly
    0.51
     количе
    0.50
     quelqu
    0.49
     рит
    0.49
    POSITIVE LOGITS
    ون
    0.60
    P
    0.60
    D
    0.60
    R
    0.59
    K
    0.59
    G
    0.53
    UC
    0.51
    M
    0.50
    5
    0.50
    Z
    0.50
    Activations Density 0.000%

    No Known Activations