© 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. 173710
    Prev
    Next
    INDEX
    Explanations

    waste management dumpster rentals

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

    descriptive phrases or specifications

    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
    т
    0.58
    น
    0.56
    к
    0.54
    н
    0.51
    мі
    0.49
    ミ
    0.48
    ೆ
    0.48
    лен
    0.47
    іб
    0.46
     काव्य
    0.46
    POSITIVE LOGITS
     it
    0.47
     ইহা
    0.44
     işlemler
    0.44
     It
    0.41
    🏤
    0.41
     contraire
    0.40
    ocyclic
    0.40
    ophytes
    0.40
     negocio
    0.40
     eutectic
    0.40
    Activations Density 0.002%

    No Known Activations