© 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. 3498
    Prev
    Next
    INDEX
    Explanations

    the other

    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
     грун
    1.55
     filha
    1.46
    фан
    1.45
    斥
    1.45
     Compounds
    1.38
     Соб
    1.38
    گرد
    1.37
    пр
    1.36
    伏
    1.36
     carp
    1.36
    POSITIVE LOGITS
    executive
    1.87
    ECUTIVE
    1.84
     EXECUTIVE
    1.83
     Executives
    1.78
     executive
    1.67
    Executive
    1.67
     Executive
    1.59
     executives
    1.52
     ejecutivo
    1.49
     tabular
    1.45
    Activations Density 0.017%

    No Known Activations