© 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. 126708
    Prev
    Next
    INDEX
    Explanations

    major comedy clubs

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

    unique, authentic, or descriptive narratives

    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
    iste
    0.47
     Ferris
    0.46
     Diaspora
    0.44
     Response
    0.44
     Lately
    0.43
    t
    0.43
     Without
    0.43
     pil
    0.42
    evan
    0.42
     Chevron
    0.42
    POSITIVE LOGITS
     authentically
    0.57
    unico
    0.54
     centrally
    0.52
     subdue
    0.52
     supremely
    0.49
     einzigen
    0.48
     অনুষ্ঠিত
    0.48
     optimised
    0.47
     ада
    0.47
     អ
    0.46
    Activations Density 0.002%

    No Known Activations