© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 200579
    Prev
    Next
    INDEX
    Explanations

    identifying language or possession

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quela
    0.37
     always
    0.36
     fit
    0.36
    ה
    0.36
    quele
    0.36
     original
    0.35
     used
    0.35
    ח
    0.34
     gerais
    0.34
     better
    0.33
    POSITIVE LOGITS
     عندك
    0.43
     లేదా
    0.41
     तुमच्या
    0.41
     உங்கள்
    0.40
     அல்லது
    0.39
     কিংবা
    0.39
    ंक्शन
    0.39
    ঘুম
    0.38
     किंवा
    0.38
     Sunak
    0.38
    Activations Density 0.003%

    No Known Activations