© 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. 102243
    Prev
    Next
    INDEX
    Explanations

    external graphics

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

    sections or headings

    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
     teorías
    0.58
     símbolos
    0.57
     الاستفهام
    0.56
     consecuencias
    0.55
     twierd
    0.54
     શ
    0.52
     ideales
    0.51
    মন্ত্রীর
    0.51
     História
    0.50
    什么
    0.50
    POSITIVE LOGITS
    aphore
    0.47
     effluent
    0.44
     preparatory
    0.44
     eval
    0.43
     mats
    0.41
    ml
    0.41
     LONDON
    0.41
    4
    0.41
     spotting
    0.41
     checkpoint
    0.41
    Activations Density 0.000%

    No Known Activations