© 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. 224553
    Prev
    Next
    INDEX
    Explanations

    Our Father

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

    medium to high importance

    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
     وإ
    0.50
     كثير
    0.49
    ادا
    0.47
     امشي
    0.47
     كتير
    0.47
     إ
    0.47
    لي
    0.47
     يكون
    0.46
     Schnee
    0.46
     كال
    0.46
    POSITIVE LOGITS
    원
    0.54
    ма
    0.52
     corroborated
    0.52
    prox
    0.50
    пис
    0.50
    начала
    0.50
    пер
    0.49
    olytic
    0.49
    academic
    0.47
    weekday
    0.47
    Activations Density 0.003%

    No Known Activations