© 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. 50987
    Prev
    Next
    INDEX
    Explanations

    raw materials and cost optimization

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

    themes and ethical exploration

    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
     Rim
    0.45
     Ernst
    0.44
    쉽
    0.43
    eol
    0.42
    assessment
    0.42
    삐
    0.42
    建议
    0.41
    企业
    0.41
    cą
    0.41
    assess
    0.40
    POSITIVE LOGITS
     turkeys
    0.47
     relieve
    0.45
     sizable
    0.45
     championnat
    0.44
     relieves
    0.43
     gevallen
    0.43
     femen
    0.43
     failures
    0.42
     descends
    0.42
     tumultuous
    0.42
    Activations Density 0.000%

    No Known Activations