© 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. 67282
    Prev
    Next
    INDEX
    Explanations

    average, less than, normally, time

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

    exploit, fascinate, invest, supplement

    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
    i
    0.48
    ?
    0.44
    Calif
    0.43
    شك
    0.43
     Alcat
    0.43
    !
    0.42
    ي
    0.41
    👧
    0.41
    Anne
    0.41
    ihe
    0.41
    POSITIVE LOGITS
    adisu
    0.46
     giữa
    0.45
     よく
    0.44
     உடலில்
    0.44
     advantageous
    0.44
     цере
    0.44
     adecuados
    0.44
     लिपि
    0.43
     публі
    0.43
     bronce
    0.43
    Activations Density 0.000%

    No Known Activations