© 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. 188245
    Prev
    Next
    INDEX
    Explanations

    immediate assistance, out soundly

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

    sell unused items

    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
    وس
    0.49
     ஆட்சி
    0.46
    ਤਰ
    0.46
     stemmed
    0.45
     Đế
    0.45
     Umsetzung
    0.43
     एकमात्र
    0.43
    ‌و
    0.43
     والتي
    0.42
     تلك
    0.42
    POSITIVE LOGITS
    𒂊
    0.48
     접
    0.47
     sufficiently
    0.46
     appreciably
    0.46
     tolerable
    0.46
     excitatory
    0.46
     lateribus
    0.45
     srand
    0.45
     충분
    0.45
     adenos
    0.44
    Activations Density 0.003%

    No Known Activations