© 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. 30793
    Prev
    Next
    INDEX
    Explanations

    financial or numerical data

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

    day, time references, 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
     మాత్రమే
    0.48
     Soy
    0.46
    Logan
    0.45
     Redeemer
    0.45
     только
    0.44
    ଭ
    0.44
     Whip
    0.44
    犹豫
    0.43
     Gouver
    0.43
     Chúa
    0.43
    POSITIVE LOGITS
    (
    0.52
     automaton
    0.51
     keychain
    0.50
     diurnal
    0.50
     gauss
    0.48
     kivy
    0.48
     python
    0.47
     nonzero
    0.46
     newline
    0.46
     extremal
    0.46
    Activations Density 0.000%

    No Known Activations