© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 2541
    Prev
    Next
    INDEX
    Explanations

    mathematical approximations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
     prize
    0.73
     २००
    0.68
     ততদিন
    0.68
     tells
    0.67
     Dernière
    0.67
     १००
    0.66
    四十
    0.65
     Fallout
    0.65
     Pace
    0.65
     unfortunate
    0.64
    POSITIVE LOGITS
    ##
    0.74
    subsection
    0.72
    %.
    0.72
    verg
    0.71
    Versioning
    0.69
     %.
    0.66
    ueness
    0.63
    nested
    0.63
    แข็ง
    0.63
    ver
    0.63
    Activations Density 0.244%

    No Known Activations