© 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. 204341
    Prev
    Next
    INDEX
    Explanations

    after certain words

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

    languages spoken

    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
    ího
    0.49
     Nhiều
    0.48
    ▟
    0.46
    ualmente
    0.45
     nhiều
    0.45
     createUser
    0.45
     umani
    0.45
    <mask>
    0.45
     sóng
    0.44
     LIMIT
    0.44
    POSITIVE LOGITS
    quadratic
    0.44
    cellular
    0.43
    വിന്റെ
    0.43
    த்தர
    0.41
    隅
    0.41
    lateral
    0.41
    passenger
    0.41
    jars
    0.40
    spots
    0.40
    лась
    0.39
    Activations Density 0.001%

    No Known Activations