© 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. 7584
    Prev
    Next
    INDEX
    Explanations

    holds the

    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
     بودن
    1.95
    讓他
    1.93
    让他
    1.89
    这一点
    1.87
    ">→</
    1.79
     bunun
    1.76
    욕
    1.76
    这点
    1.76
     nächste
    1.75
     שהוא
    1.74
    POSITIVE LOGITS
     principally
    2.33
     predominantly
    2.08
     sixteen
    1.98
     nineteen
    1.97
     alphabetically
    1.92
     nominally
    1.89
     seventeen
    1.89
     chiefly
    1.89
     aggregated
    1.89
     primarily
    1.87
    Activations Density 0.148%

    No Known Activations