© 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. 151816
    Prev
    Next
    INDEX
    Explanations

    arrange for

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

    experimenting with variations

    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
    и
    0.45
    notin
    0.45
    coma
    0.44
     незавершена
    0.42
    শুর
    0.41
    Written
    0.40
    ?..
    0.40
    Similarly
    0.39
    嶠
    0.39
    淩
    0.39
    POSITIVE LOGITS
     passwd
    0.49
    デバイス
    0.49
     cepat
    0.47
     دستگاه
    0.47
     powertrain
    0.45
     dispoz
    0.44
    ्मण
    0.44
    だったので
    0.43
     انرژی
    0.43
     devices
    0.43
    Activations Density 0.001%

    No Known Activations