© 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. 213014
    Prev
    Next
    INDEX
    Explanations

    alleged murder, microwave oven

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

    basic essential answer

    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
    放大
    0.48
    шире
    0.48
    作为
    0.48
    вла
    0.47
    нор
    0.47
    扔
    0.47
     Quantification
    0.47
     Linking
    0.46
     attivo
    0.46
     Merkez
    0.46
    POSITIVE LOGITS
     صنعت
    0.48
    gesetz
    0.48
    Buch
    0.47
    メガネ
    0.47
    kook
    0.46
     axiomatic
    0.46
    birds
    0.46
     vuos
    0.45
     프
    0.45
    Gonzalez
    0.45
    Activations Density 0.000%

    No Known Activations