© 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. 33685
    Prev
    Next
    INDEX
    Explanations

    asteroids by number

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

    area measurements in square kilometers and miles

    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
     unites
    0.52
     équipe
    0.48
    tts
    0.48
    تن
    0.46
    cendo
    0.45
    ب
    0.45
     heures
    0.45
     époque
    0.45
     École
    0.45
    onces
    0.44
    POSITIVE LOGITS
     sahib
    0.48
    划分
    0.47
    劃
    0.47
     внимания
    0.46
     sogen
    0.45
     anuv
    0.45
    కాం
    0.45
    很大的
    0.44
     TRANSPORTURI
    0.44
     遅く
    0.44
    Activations Density 0.000%

    No Known Activations