© 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. 95925
    Prev
    Next
    INDEX
    Explanations

    created another

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

    language variations explanations

    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
     கிழக்கு
    0.54
     окна
    0.54
    kušen
    0.53
    ૩
    0.53
     नॉट
    0.52
     मिळते
    0.52
     दलों
    0.51
    czyć
    0.51
     जोड़ों
    0.50
    де
    0.50
    POSITIVE LOGITS
    -
    0.53
     bandwidth
    0.51
    "
    0.51
     academic
    0.47
     image
    0.47
     hospital
    0.45
    Parse
    0.45
     generated
    0.45
     components
    0.44
    ”
    0.44
    Activations Density 0.000%

    No Known Activations