© 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. 237978
    Prev
    Next
    INDEX
    Explanations

    foreign characters or phrases

    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
     diatomic
    0.55
     статисти
    0.51
     +/-
    0.49
    licks
    0.49
     hypoxia
    0.49
     olen
    0.49
     PEM
    0.48
     DMS
    0.48
     antica
    0.48
     irresistible
    0.47
    POSITIVE LOGITS
    警
    0.54
    昂
    0.52
    যাত্রা
    0.51
    emar
    0.49
    員
    0.47
    彊
    0.47
    ောင်း
    0.46
    etor
    0.45
    eteers
    0.45
    เต
    0.45
    Activations Density 0.000%

    No Known Activations