© 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. 191745
    Prev
    Next
    INDEX
    Explanations

    describing conditions and roles

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

    behavior or meaning

    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
     шанс
    0.42
     pulver
    0.42
    మై
    0.41
     lipid
    0.41
     анализ
    0.41
    uni
    0.40
     uni
    0.40
    u
    0.40
     hydros
    0.39
    iti
    0.39
    POSITIVE LOGITS
     他们
    0.49
     Multiply
    0.46
     रिश्तों
    0.46
     ಭಾಗ
    0.46
    🕴
    0.46
    wxr
    0.46
     मल्टीप्लाई
    0.45
    carros
    0.44
    Timestamp
    0.44
    訥
    0.44
    Activations Density 0.000%

    No Known Activations