© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13436
    Prev
    Next
    INDEX
    Explanations

    development and authorization

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

    than factoring

    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_16k_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
     Britons
    0.56
     tuberculous
    0.47
     inhibited
    0.45
     灬
    0.45
    besie
    0.45
     SUBSTITUTE
    0.45
     inz
    0.45
    rne
    0.44
     spines
    0.44
     inlaid
    0.44
    POSITIVE LOGITS
    ونی
    0.53
    開発
    0.52
     மற்றும்
    0.49
    的产品
    0.49
    🫡
    0.47
     প্রোগ্রাম
    0.46
    나
    0.46
     répart
    0.46
    Metaxy
    0.45
    avadoc
    0.45
    Activations Density 0.008%

    No Known Activations