© 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. 189532
    Prev
    Next
    INDEX
    Explanations

    phrases of specific words followed by others

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

    barely knew, approval ratings, African bush

    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
    ounded
    0.50
    assapi
    0.48
    ouwen
    0.47
    是从
    0.46
    是将
    0.46
    алы
    0.45
    еве
    0.45
    ͹
    0.45
    ولندا
    0.45
    alma
    0.45
    POSITIVE LOGITS
     segu
    0.50
     ρ
    0.48
     a
    0.47
     metric
    0.46
     constrain
    0.46
     magic
    0.45
    car
    0.45
     com
    0.44
     really
    0.44
     disconnection
    0.44
    Activations Density 0.000%

    No Known Activations