© 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. 128236
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases and clauses

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

    things followed by words

    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
    open
    0.46
    с
    0.46
    校
    0.44
    ่า
    0.43
    лт
    0.42
     guill
    0.42
    cambrian
    0.41
    ils
    0.40
    ке
    0.40
    ко
    0.39
    POSITIVE LOGITS
     Inhalte
    0.54
     উপাদান
    0.54
     klient
    0.51
     qualcosa
    0.50
    絭
    0.48
     aktywn
    0.48
    aties
    0.47
     måde
    0.46
     åt
    0.46
     देखिए
    0.45
    Activations Density 0.001%

    No Known Activations