© 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. 4416
    Prev
    Next
    INDEX
    Explanations

    start, beginning, road, downstream, governors

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

    before or pre

    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
     seguimiento
    0.46
    පි
    0.45
     jsou
    0.44
     ט
    0.43
    卒業
    0.42
     stopni
    0.41
    深圳市
    0.41
     خ
    0.40
    どれ
    0.40
     serii
    0.40
    POSITIVE LOGITS
    **,
    0.46
    ¹,
    0.46
     или
    0.45
     instead
    0.44
    instead
    0.42
     earliest
    0.42
    unshift
    0.42
     बजाय
    0.41
    inline
    0.40
     favoured
    0.40
    Activations Density 0.000%

    No Known Activations