© 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. 146394
    Prev
    Next
    INDEX
    Explanations

    brands reported attempting environment compost

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

    materials, IT, AI, food

    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
    PRESSURE
    0.47
    Repe
    0.46
    セール
    0.46
    Pile
    0.46
     ड
    0.45
    św
    0.45
     scrapes
    0.44
     ไหร่
    0.44
    pile
    0.43
    Chan
    0.43
    POSITIVE LOGITS
    ඬ
    0.45
    ajú
    0.45
    ເຮ
    0.44
    obox
    0.43
     tendremos
    0.43
    ající
    0.43
     వాహ
    0.43
     అందు
    0.42
    တင်
    0.42
     vão
    0.42
    Activations Density 0.000%

    No Known Activations