© 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. 37017
    Prev
    Next
    INDEX
    Explanations

    crushing rocks

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

    rules and restrictions

    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
     gyárt
    0.46
     изделий
    0.45
     banca
    0.45
     propietarios
    0.45
     вероятность
    0.43
     chauss
    0.43
     bolas
    0.42
    䂧
    0.41
     अधिकारों
    0.41
     نبود
    0.40
    POSITIVE LOGITS
    se
    0.51
     Classroom
    0.44
     Teaching
    0.43
     Listening
    0.43
     अध्या
    0.43
    5
    0.42
    re
    0.41
     Pract
    0.41
     Practice
    0.41
    1
    0.41
    Activations Density 0.000%

    No Known Activations