© 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. 76244
    Prev
    Next
    INDEX
    Explanations

    specific words and subsequent punctuation

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

    consecutive integers or patches

    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
     vuurp
    0.54
     sabi
    0.49
    ibc
    0.47
    Width
    0.47
     मैक
    0.47
     využ
    0.46
    tery
    0.46
    X
    0.45
     trzech
    0.45
    gabe
    0.44
    POSITIVE LOGITS
     internalized
    0.46
    साथ
    0.44
    {
    0.43
     materialized
    0.43
     유리
    0.42
     материа
    0.41
     अगला
    0.41
    也就是说
    0.41
     грав
    0.41
    」，
    0.41
    Activations Density 0.000%

    No Known Activations