© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 172544
    Prev
    Next
    INDEX
    Explanations

    protection possible

    np_acts-logits-general · gemini-2.5-flash-lite

    explaining relationships and processes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     éves
    0.55
     institucional
    0.52
     zdoby
    0.52
    撬
    0.52
     provenienti
    0.51
     SALT
    0.48
     मिळू
    0.48
    മുണ്ട്
    0.48
     SKIN
    0.47
     taxing
    0.46
    POSITIVE LOGITS
    :
    0.54
    .
    0.54
    ;
    0.50
    ή
    0.45
    You
    0.45
    I
    0.44
    (
    0.44
     -
    0.43
    It
    0.43
    #
    0.43
    Activations Density 0.001%

    No Known Activations