© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 420
    Prev
    Next
    INDEX
    Explanations

    I understand

    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
    眠
    0.63
     scritto
    0.63
    WHEREAS
    0.62
    drawiam
    0.62
     Seit
    0.62
     scrive
    0.61
     estejam
    0.61
     Written
    0.61
    Pues
    0.61
     acompanhar
    0.60
    POSITIVE LOGITS
    jquery
    0.55
    marès
    0.54
    Validation
    0.52
    소
    0.51
    مار
    0.49
    Lapangan
    0.49
    Confirmation
    0.47
    Process
    0.47
    Processing
    0.46
    激安
    0.46
    Activations Density 0.424%

    No Known Activations