© 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. 190327
    Prev
    Next
    INDEX
    Explanations

    French Jewish and Masonic library collections

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

    understanding specific topics

    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
     використання
    0.55
     использование
    0.52
     Я
    0.50
     וא
    0.50
    碖
    0.49
    Я
    0.48
    綗
    0.47
     obviously
    0.47
     используя
    0.46
     REIT
    0.46
    POSITIVE LOGITS
    rishna
    0.44
    ատ
    0.44
    OM
    0.43
    oze
    0.43
    στι
    0.42
    ො
    0.41
    第二个
    0.41
    𝔬
    0.40
    fels
    0.40
    ้อม
    0.40
    Activations Density 0.000%

    No Known Activations