© 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. 161568
    Prev
    Next
    INDEX
    Explanations

    please visit

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

    restricted movement

    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
    ب
    0.52
    بد
    0.47
    mals
    0.45
    紆
    0.45
     oddly
    0.43
    #
    0.42
     électron
    0.42
    ுக
    0.41
    ي
    0.41
    جن
    0.41
    POSITIVE LOGITS
    rektor
    0.51
     DSLR
    0.48
     BoxFit
    0.46
     Dato
    0.45
    हालय
    0.44
     Grac
    0.42
     Molecular
    0.41
     TCP
    0.41
     삼성
    0.41
     PCIe
    0.41
    Activations Density 0.001%

    No Known Activations