© 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. 144031
    Prev
    Next
    INDEX
    Explanations

    March For Our Lives

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

    multilingual special characters

    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
     potrav
    0.57
    跟
    0.45
     kaže
    0.44
     informatique
    0.44
     üretim
    0.44
     Lithuanian
    0.44
     Latvian
    0.44
     nivel
    0.44
     étaient
    0.44
     rétréc
    0.44
    POSITIVE LOGITS
    с
    0.46
    са
    0.45
    ва
    0.45
    пс
    0.44
     концерт
    0.44
    वाह
    0.43
    пси
    0.43
     брат
    0.43
     музи
    0.42
    govor
    0.41
    Activations Density 0.001%

    No Known Activations