© 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. 1778
    Prev
    Next
    INDEX
    Explanations

    questions and academic essays

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

    write code or text

    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
     tasty
    0.39
    ître
    0.38
    সরকারী
    0.37
    präsident
    0.36
     تاہم
    0.36
    eliest
    0.34
    互联网档案馆
    0.34
    腥
    0.33
     embassy
    0.33
     gesetz
    0.33
    POSITIVE LOGITS
     Q
    0.52
     PLEASE
    0.48
     QUESTION
    0.45
     MCQ
    0.44
    Q
    0.44
     ONLY
    0.43
    PLEASE
    0.43
    ДА
    0.43
    Explain
    0.42
     س
    0.41
    Activations Density 0.000%

    No Known Activations