© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1565
    Prev
    Next
    INDEX
    Explanations

    adding or arithmetic

    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
     ——
    0.71
    ismes
    0.66
    ︠
    0.65
    ](../
    0.60
    ("/");
    0.59
    ('/
    0.58
    перь
    0.57
     ―
    0.55
    எல்
    0.55
    ](./
    0.55
    POSITIVE LOGITS
    +
    4.99
     +
    4.58
    ＋
    3.97
    +.
    3.78
    +,
    3.73
     $+
    3.71
     $+$
    3.71
    +(
    3.66
    +$
    3.51
    +\
    3.44
    Activations Density 0.274%

    No Known Activations