© 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. 126058
    Prev
    Next
    INDEX
    Explanations

    downloading files or content

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

    numbers and identifiers

    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
     vehicular
    0.50
    aguan
    0.46
    jButton
    0.46
    බා
    0.46
     transportation
    0.45
     খেলার
    0.44
     preventative
    0.44
    蠵
    0.44
    aterial
    0.43
     पि
    0.43
    POSITIVE LOGITS
    ۵
    0.49
     trois
    0.48
     üç
    0.47
     œuvres
    0.47
     naudoj
    0.46
     OCPP
    0.45
     charakter
    0.44
    データの
    0.44
     drei
    0.44
     composants
    0.43
    Activations Density 0.000%

    No Known Activations