© 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. 70603
    Prev
    Next
    INDEX
    Explanations

    end of phrase punctuation

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

    target x, y coordinates

    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
    依旧
    0.47
    🙉
    0.47
     vẫn
    0.47
    สาย
    0.45
    สัญญาณ
    0.45
    मॉन
    0.44
     récent
    0.44
     റോ
    0.44
    نش
    0.43
    етка
    0.43
    POSITIVE LOGITS
    :
    0.53
    .
    0.52
    n
    0.51
    '
    0.51
    .:
    0.50
    _
    0.49
    v
    0.49
    :.
    0.48
    ly
    0.48
    vette
    0.47
    Activations Density 0.000%

    No Known Activations