© 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. 1378
    Prev
    Next
    INDEX
    Explanations

    list items following separators

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

    risk of closure

    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
     με
    0.58
     ((
    0.52
     ν
    0.52
    ife
    0.50
    ocus
    0.47
    )
    0.47
     (
    0.46
     τε
    0.45
     শুনি
    0.45
     caricature
    0.44
    POSITIVE LOGITS
     Jó
    0.50
     léz
    0.49
    솎
    0.49
    众人
    0.47
     Förderung
    0.47
    ದಾ
    0.47
     Éd
    0.47
    BinBuf
    0.46
     článku
    0.45
    써
    0.45
    Activations Density 0.000%

    No Known Activations