© 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. 220784
    Prev
    Next
    INDEX
    Explanations

    Title IV funds

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

    depending on variations

    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
     Oficina
    0.49
     B
    0.48
     NUMBER
    0.46
     presente
    0.45
     ਵੀ
    0.44
     Meny
    0.44
     forthcoming
    0.44
     yorum
    0.44
     ओनली
    0.43
     Nascimento
    0.43
    POSITIVE LOGITS
    让
    0.51
    我在
    0.48
    Combat
    0.45
    我们在
    0.43
    Risk
    0.43
    combat
    0.42
    Schedule
    0.42
    Survival
    0.39
    可以让
    0.39
    Parts
    0.39
    Activations Density 0.001%

    No Known Activations