© 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. 67703
    Prev
    Next
    INDEX
    Explanations

    public class Program

    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
    jahteraan
    0.44
    ̶
    0.43
    をご確認
    0.41
    शाही
    0.40
     तौर
    0.39
     ﷺ
    0.39
     dõi
    0.39
     '<%=
    0.39
    িয়াল
    0.38
    laquo
    0.38
    POSITIVE LOGITS
     दहा
    0.43
     Professors
    0.42
    recer
    0.41
     கண்டி
    0.41
     typedef
    0.41
    쿤
    0.40
     بن
    0.39
     professor
    0.39
     پکڑ
    0.39
    尃
    0.38
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.