© 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. 164869
    Prev
    Next
    INDEX
    Explanations

    long periods

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

    newline character

    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
    lig
    0.52
     monet
    0.49
     impuls
    0.48
     antipsych
    0.46
     tensor
    0.44
     ў
    0.43
     romant
    0.43
     vikt
    0.42
     stormed
    0.42
     doct
    0.42
    POSITIVE LOGITS
     Puoi
    0.61
     ότι
    0.51
     انك
    0.51
    ২৭
    0.51
     کشور
    0.49
    嘏
    0.48
     Chỉ
    0.47
     Nếu
    0.47
     Surveys
    0.46
     അമേരിക്ക
    0.46
    Activations Density 0.000%

    No Known Activations