© 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. 2689
    Prev
    Next
    INDEX
    Explanations

    dates (month day, year)

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

    ordinal day numbers

    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
     .
    0.44
    .
    0.42
     cfp
    0.38
    क
    0.38
    ()
    0.38
    can
    0.36
    cd
    0.36
     UNI
    0.35
     ventre
    0.34
     другое
    0.34
    POSITIVE LOGITS
    匤
    0.42
    跟
    0.41
    имуще
    0.40
    bruch
    0.40
     جائیں
    0.38
     Direito
    0.38
    िकता
    0.38
    <unused40>
    0.37
    direito
    0.36
     решать
    0.36
    Activations Density 0.031%

    No Known Activations