© 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. 172151
    Prev
    Next
    INDEX
    Explanations

    For example

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

    taxes or online forum

    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
    мага
    0.52
    옴
    0.52
     Quadrupèdes
    0.50
    Aph
    0.48
     कक्क
    0.47
    мпаваць
    0.47
     Mattress
    0.46
    اك
    0.46
    夼
    0.46
    arnos
    0.45
    POSITIVE LOGITS
     indel
    0.56
     duck
    0.50
     on
    0.49
     gaining
    0.49
    v
    0.49
     part
    0.48
     every
    0.48
     recessed
    0.48
     structural
    0.47
     outliers
    0.47
    Activations Density 0.000%

    No Known Activations