© 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. 204685
    Prev
    Next
    INDEX
    Explanations

    switch to charge

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

    why, will, companies, flu, China, significantly

    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
    oph
    0.51
     Lyrics
    0.50
     Prague
    0.49
     Christina
    0.49
     P
    0.48
     Spit
    0.48
     PL
    0.48
     Czech
    0.48
     This
    0.48
     From
    0.47
    POSITIVE LOGITS
     corretamente
    0.48
    respArray
    0.47
    ません
    0.47
     roadway
    0.46
    toFloat
    0.45
    🈺
    0.45
    可能です
    0.44
     raya
    0.44
    keyValue
    0.44
    SpecID
    0.43
    Activations Density 0.001%

    No Known Activations