© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 6583
    Prev
    Next
    INDEX
    Explanations

    process and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
    hala
    1.65
    modification
    1.65
    )^{*}$
    1.51
     alterações
    1.48
    fection
    1.48
    erah
    1.47
    public
    1.47
    ième
    1.46
     tử
    1.46
    +')
    1.44
    POSITIVE LOGITS
     sounding
    1.35
     proceeding
    1.34
    mentare
    1.23
    скетбол
    1.23
     poised
    1.21
     progressing
    1.20
     starting
    1.20
     heading
    1.20
    STERBEDATUM
    1.19
     well
    1.19
    Activations Density 0.077%

    No Known Activations