© 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. 13930
    Prev
    Next
    INDEX
    Explanations

    closing punctuation marks

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

    ensure, like, with, manage, task

    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
     آ
    0.47
     لگے
    0.46
     displeasure
    0.46
     splendour
    0.42
     florist
    0.42
     カラー
    0.40
    RowCount
    0.40
    挑戰
    0.40
     पहिली
    0.39
     見
    0.39
    POSITIVE LOGITS
    )
    0.45
    ين
    0.40
     കഴിയ
    0.40
    xlim
    0.40
    you
    0.39
    ^{*}
    0.39
    ),\
    0.39
    \]
    0.39
    ydia
    0.39
    +\
    0.38
    Activations Density 0.001%

    No Known Activations