© 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. 149699
    Prev
    Next
    INDEX
    Explanations

    proclaims, immigration, umbilical cord, linear screen

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

    special cases

    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
    acaks
    0.42
    ignor
    0.41
     alcoholism
    0.41
    Sing
    0.41
    Ses
    0.41
     autour
    0.40
    า
    0.40
    🥴
    0.39
     ambitions
    0.39
    webp
    0.39
    POSITIVE LOGITS
     جميل
    0.55
    bt
    0.52
    瘦
    0.50
    jte
    0.48
     mooie
    0.47
    certified
    0.47
     మనం
    0.46
     certify
    0.46
    мы
    0.46
     $("#
    0.46
    Activations Density 0.002%

    No Known Activations