© 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. 66388
    Prev
    Next
    INDEX
    Explanations

    freezer buying

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

    four lines

    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
    硞
    0.48
     सिंपली
    0.48
     ಏನು
    0.47
     त्य
    0.47
     ಯು
    0.47
     시설
    0.47
    啜
    0.47
     러시아
    0.47
     неред
    0.46
     उल्लंघन
    0.46
    POSITIVE LOGITS
     Entomology
    0.56
     excelencia
    0.47
    Font
    0.47
    None
    0.46
    ↵
    0.44
    FRI
    0.44
     Metropolitana
    0.44
    /
    0.44
     Comunicación
    0.44
    ’
    0.44
    Activations Density 0.000%

    No Known Activations