© 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. 107473
    Prev
    Next
    INDEX
    Explanations

    syrup or Clause

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

    saying or Oh followed by punctuation

    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
    ப்ப
    0.50
    ན
    0.49
    વિ
    0.49
     chọn
    0.45
     membranes
    0.45
    を経
    0.44
    に近い
    0.44
     Membranes
    0.43
    ли
    0.43
    选择了
    0.43
    POSITIVE LOGITS
     zasad
    0.58
     serum
    0.48
    etition
    0.47
     हैज
    0.47
    သမ
    0.47
     sla
    0.46
     ℝ
    0.46
     Ag
    0.45
     presc
    0.45
     cré
    0.45
    Activations Density 0.001%

    No Known Activations