© 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. 197372
    Prev
    Next
    INDEX
    Explanations

    primary components, women rise, most creepy

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

    coroutine or Git conflict markers

    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
    ;
    0.57
     Closet
    0.50
     Touching
    0.48
    %;
    0.46
     Portrait
    0.46
     Instal
    0.46
     Touch
    0.45
    ias
    0.44
    avoir
    0.44
     Caste
    0.43
    POSITIVE LOGITS
     अभिनेत्री
    0.50
    ドライバー
    0.48
     pandémie
    0.48
    ファン
    0.46
    thebibliography
    0.45
     línea
    0.45
    يدة
    0.44
    ワン
    0.44
    せ
    0.44
     nervously
    0.44
    Activations Density 0.001%

    No Known Activations