© 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. 6707
    Prev
    Next
    INDEX
    Explanations

    swap meals

    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
    ־
    1.83
    ỏ
    1.60
    ␣
    1.56
     inscreve
    1.54
    ‮
    1.54
    crocodile
    1.52
    ‒
    1.50
    ⁠
    1.49
     —,
    1.49
    phosphat
    1.46
    POSITIVE LOGITS
    量的
    1.15
     previos
    1.13
     ppl
    1.07
     sya
    1.06
    /
    1.06
    量は
    1.06
     gathering
    1.06
    量を
    1.05
     kinda
    1.05
     BASIS
    1.00
    Activations Density 0.205%

    No Known Activations