© 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. 96987
    Prev
    Next
    INDEX
    Explanations

    sensitive to temperature and acidity

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

    safe, built, licensing

    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
     rained
    0.48
     féri
    0.47
     construed
    0.46
    дания
    0.45
    陏
    0.45
     misled
    0.45
    fragt
    0.44
    ürdig
    0.44
     секрета
    0.44
    дян
    0.44
    POSITIVE LOGITS
    2
    0.51
    or
    0.47
     afferm
    0.46
     Nome
    0.46
     isotope
    0.45
    1
    0.44
    ท
    0.44
    Ն
    0.44
     uso
    0.44
    ವ
    0.43
    Activations Density 0.000%

    No Known Activations