© 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. 1930
    Prev
    Next
    INDEX
    Explanations

    drives, park, palace, world, games

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

    words and non-english characters

    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
     a
    0.35
     you
    0.32
    kaggle
    0.31
     jūs
    0.30
     usted
    0.29
     ona
    0.29
     agir
    0.29
    ().
    0.29
     aneur
    0.29
     an
    0.28
    POSITIVE LOGITS
    ла
    0.36
    d
    0.36
    ad
    0.36
    us
    0.35
    ac
    0.34
    на
    0.33
    et
    0.32
    ला
    0.32
    am
    0.31
    ag
    0.30
    Activations Density 0.689%

    No Known Activations