© 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. 191391
    Prev
    Next
    INDEX
    Explanations

    months after dates

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

    dates with numbers and slashes

    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
    man
    0.48
    หรือ
    0.47
    par
    0.47
    nt
    0.46
     অথবা
    0.46
    category
    0.45
    e
    0.44
    或者
    0.43
    student
    0.43
    /
    0.43
    POSITIVE LOGITS
     tę
    0.51
     ilość
    0.47
     tonnage
    0.46
     hosszú
    0.46
    윕
    0.46
     দিনে
    0.45
     faisons
    0.45
    StrTo
    0.44
     toughness
    0.44
     hátsó
    0.43
    Activations Density 0.006%

    No Known Activations