© 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. 76943
    Prev
    Next
    INDEX
    Explanations

    wrapped in plastic

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

    bank manager, robbery, gun pointed

    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
     hypertext
    0.49
    ویان
    0.46
    ֆ
    0.46
     rather
    0.42
    抛
    0.42
     Bevan
    0.41
     kawasan
    0.41
     elaboration
    0.41
    વાસ
    0.40
     Brokers
    0.40
    POSITIVE LOGITS
    ľad
    0.47
     रियलिटी
    0.45
    checkout
    0.45
    getColor
    0.44
     aniversário
    0.43
    Ꮎ
    0.43
     वृद्धा
    0.42
    érc
    0.42
    atorul
    0.42
     నుండి
    0.41
    Activations Density 0.000%

    No Known Activations