© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 4399
    Prev
    Next
    INDEX
    Explanations

    own + personal experiences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
    kani
    1.33
    hr
    1.31
    ze
    1.30
    hrs
    1.29
    ۶
    1.25
    ۱
    1.20
    گرم
    1.18
    levation
    1.16
    vals
    1.14
    versch
    1.11
    POSITIVE LOGITS
    blooded
    1.97
     afirmar
    1.71
     reconhe
    1.69
     compris
    1.66
    BatchNorm
    1.64
     escala
    1.63
    ̈́
    1.62
     homenagem
    1.62
    ඤ
    1.62
     établie
    1.60
    Activations Density 0.179%

    No Known Activations