© 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. 51606
    Prev
    Next
    INDEX
    Explanations

    brands and services names

    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
    ’;
    0.48
    ट्ट
    0.46
     Macbeth
    0.45
     १६
    0.43
     вариантов
    0.43
     '>'
    0.43
    otom
    0.43
    olol
    0.42
     रखरखाव
    0.42
     उपलब्
    0.42
    POSITIVE LOGITS
    ية
    0.50
    ча
    0.46
    লেট
    0.45
     راست
    0.45
    ᅯ
    0.45
    يريا
    0.44
    ំណ
    0.44
    ফ
    0.43
     giornal
    0.43
    يدا
    0.42
    Activations Density 0.000%

    No Known Activations