© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14905
    Prev
    Next
    INDEX
    Explanations

    Calves, how to, travel, did, Brittenford, the, TOP, Am, December, DO

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

    punishment for theft

    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_16k_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
    cektir
    0.42
    izacja
    0.40
     डेब्यू
    0.38
    izare
    0.37
    numberOf
    0.36
    ću
    0.35
    respArray
    0.35
    {%
    0.35
    Questa
    0.35
    erunner
    0.35
    POSITIVE LOGITS
     अन्यथा
    0.36
     moistened
    0.35
     overrated
    0.34
    ਟੀ
    0.34
    fad
    0.34
     цен
    0.34
     लोकेशन
    0.33
    बन
    0.33
    んば
    0.33
    డని
    0.33
    Activations Density 0.064%

    No Known Activations