© 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. 200659
    Prev
    Next
    INDEX
    Explanations

    certified, agencies, allows

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

    recent prices, naturally occurring, Before you

    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
    વિ
    0.52
     inkább
    0.51
    ي
    0.51
    פ
    0.50
    ט
    0.48
     almo
    0.47
     erbjud
    0.46
     ג
    0.46
    不过
    0.46
    િત
    0.46
    POSITIVE LOGITS
     Naples
    0.43
    hetic
    0.42
    www
    0.41
     Wordsworth
    0.40
     Fractals
    0.40
    HTML
    0.40
     Hammer
    0.39
     Certified
    0.39
    LayoutParams
    0.39
    you
    0.39
    Activations Density 0.000%

    No Known Activations