© 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. 128638
    Prev
    Next
    INDEX
    Explanations

    freezers, double showers, felspar

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

    numbers followed by units or operations

    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
     ndani
    0.53
     swojej
    0.47
     swoich
    0.46
    _
    0.45
     wszystkich
    0.45
    nm
    0.43
     pestaña
    0.43
     esclus
    0.43
     sonrası
    0.43
    യോഗ
    0.42
    POSITIVE LOGITS
    inja
    0.48
    殞
    0.46
    陖
    0.45
    㣫
    0.44
    iera
    0.44
    ätzung
    0.44
    諫
    0.44
    䈤
    0.44
     ആണ
    0.43
    烪
    0.43
    Activations Density 0.001%

    No Known Activations