© 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. 238278
    Prev
    Next
    INDEX
    Explanations

    distinguish intel information + regular published

    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
    ל
    0.51
    Ober
    0.46
    StarService
    0.43
     کئے
    0.43
    InOut
    0.43
    規
    0.43
    لین
    0.42
    ل
    0.42
    その
    0.41
     ಶಾ
    0.41
    POSITIVE LOGITS
     ".
    0.49
    طة
    0.47
    daad
    0.46
     Mediterr
    0.46
    碣
    0.46
    兖
    0.46
    izhou
    0.45
    TTLE
    0.45
    тою
    0.45
     "."
    0.44
    Activations Density 0.002%

    No Known Activations