© 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. 210851
    Prev
    Next
    INDEX
    Explanations

    location markers

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

    concepts like geometry and intelligence

    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
    ks
    0.60
    ada
    0.59
    ía
    0.59
    ied
    0.57
    ath
    0.55
    ish
    0.54
    istu
    0.54
    k
    0.54
    ist
    0.54
     تقسيم
    0.54
    POSITIVE LOGITS
    محمد
    0.48
    Sun
    0.48
    Tuesday
    0.47
     interfacial
    0.47
    Santo
    0.45
     প্রত্যাখ্যান
    0.45
    に基づく
    0.45
    لی
    0.45
    สม
    0.45
     Lesen
    0.44
    Activations Density 0.001%

    No Known Activations