© 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. 12-GEMMASCOPE-2-RES-16K
    7. 6957
    Prev
    Next
    INDEX
    Explanations

    anime and figures

    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_12_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
    嗽
    1.44
     coqu
    1.35
     suffrage
    1.33
    ตุ
    1.33
    alq
    1.31
    )^{*}$
    1.28
    othiaz
    1.27
    }^{*}\
    1.25
     pulm
    1.24
     wetter
    1.24
    POSITIVE LOGITS
     Brian
    1.89
    Brian
    1.78
     Justin
    1.72
     Joshua
    1.69
    Justin
    1.58
    Joshua
    1.55
     Jason
    1.54
    Jason
    1.52
     Trimble
    1.49
     Ashley
    1.47
    Activations Density 0.034%

    No Known Activations