© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 3448
    Prev
    Next
    INDEX
    Explanations

    styled-components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_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
    CRL
    0.87
    divided
    0.86
    몇
    0.86
    VisualStudio
    0.83
    明显的
    0.82
     yú
    0.80
    Hola
    0.80
     відбувається
    0.80
     quinquina
    0.80
    ↵
    0.79
    POSITIVE LOGITS
     अ
    0.81
    ieth
    0.72
     forward
    0.71
     treads
    0.71
    йте
    0.68
     Validate
    0.68
     অ
    0.67
     Keep
    0.66
    デザ
    0.66
     civic
    0.66
    Activations Density 0.000%

    No Known Activations