© 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. 161037
    Prev
    Next
    INDEX
    Explanations

    download, receipt, genetic, choose, or

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

    conditions and repetition

    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
     Ingles
    0.50
    ~\
    0.49
     Зе
    0.49
     σήμερα
    0.48
     পেছন
    0.48
     spiega
    0.47
     Palau
    0.47
    englisch
    0.46
     না
    0.46
    ກະ
    0.46
    POSITIVE LOGITS
    distortion
    0.41
     Sensitivity
    0.40
    Sensitivity
    0.39
     จำกัด
    0.39
    ึ
    0.39
     کنی
    0.39
     bpm
    0.38
     JMJD
    0.38
    elyn
    0.38
     bởi
    0.37
    Activations Density 0.001%

    No Known Activations