© 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. 91602
    Prev
    Next
    INDEX
    Explanations

    salts, time, polite, ira

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

    software, systems, and control

    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
     lighted
    0.49
     chopped
    0.47
     optically
    0.46
     bodied
    0.46
    indd
    0.45
     stripper
    0.45
     staged
    0.44
    ب
    0.44
     undamaged
    0.44
     createImage
    0.43
    POSITIVE LOGITS
    ismus
    0.50
    ă
    0.49
    še
    0.49
    í
    0.47
    篤
    0.47
    ខ្ល
    0.46
    mé
    0.46
    šet
    0.46
    gefunden
    0.45
    settes
    0.45
    Activations Density 0.001%

    No Known Activations