© 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. 1000
    Prev
    Next
    INDEX
    Explanations

    years ending in 9

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

    the number 9

    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
    ः
    0.42
    '،
    0.41
    ссия
    0.40
    ،
    0.38
     fazia
    0.38
    iomanip
    0.37
     عاما
    0.37
    mergeddata
    0.37
     latach
    0.36
     dropbox
    0.36
    POSITIVE LOGITS
    at
    0.49
    in
    0.43
    na
    0.42
    我们
    0.42
    ط
    0.40
    ନ
    0.39
    of
    0.39
    த்த
    0.39
     मौजूदा
    0.39
    자
    0.39
    Activations Density 0.014%

    No Known Activations