© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 249778
    Prev
    Next
    INDEX
    Explanations

    apps and links

    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
    Negative Logits
    פר
    0.51
    coe
    0.48
    меется
    0.47
     jedną
    0.47
    enite
    0.46
    нибудь
    0.44
    하거나
    0.44
    끗
    0.44
    (",
    0.44
    pern
    0.43
    POSITIVE LOGITS
    udra
    0.50
    aling
    0.47
    agina
    0.46
     mainten
    0.46
    ral
    0.46
    SL
    0.46
    rl
    0.45
    ruit
    0.45
     quer
    0.45
     اللّه
    0.45
    Activations Density 0.001%

    No Known Activations