© 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. 64256
    Prev
    Next
    INDEX
    Explanations

    infinitive states or property descriptions

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

    consumer surplus

    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
    ↵
    0.55
    al
    0.53
     consume
    0.48
     soy
    0.48
     consumes
    0.46
    op
    0.46
     '
    0.44
    ad
    0.44
     colon
    0.44
    consume
    0.44
    POSITIVE LOGITS
     डिजी
    0.53
    浧
    0.53
    转变
    0.49
     इच्छुक
    0.48
     equipado
    0.48
    getInput
    0.47
     হও
    0.46
     जिल्ह्यातील
    0.45
     வெப்ப
    0.45
     Guz
    0.45
    Activations Density 0.000%

    No Known Activations