© 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. 25902
    Prev
    Next
    INDEX
    Explanations

    to inaugurate

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

    rephrased or changed

    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
    ъм
    0.54
     Wanneer
    0.49
    менный
    0.48
    rata
    0.47
    dance
    0.47
    dancing
    0.47
    drum
    0.47
    с
    0.47
     финан
    0.46
    се
    0.46
    POSITIVE LOGITS
     audiences
    0.53
     a
    0.51
     breakpoints
    0.50
     offices
    0.49
     life
    0.46
     queries
    0.46
     ir
    0.45
     characters
    0.45
     ats
    0.44
     isot
    0.44
    Activations Density 0.000%

    No Known Activations