© 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. 177917
    Prev
    Next
    INDEX
    Explanations

    market demand reports

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

    density and comparisons

    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
     phòng
    0.45
    ⃣
    0.44
     நாட்கள்
    0.43
    longer
    0.42
    လေး
    0.42
    ヶ月
    0.42
    လုံး
    0.41
     bốn
    0.41
    months
    0.41
    飯
    0.41
    POSITIVE LOGITS
     perceptions
    0.47
     dane
    0.47
     occasional
    0.44
     pung
    0.44
     pul
    0.43
     komm
    0.43
     curate
    0.43
    ེ
    0.43
     Danish
    0.43
     stave
    0.43
    Activations Density 0.004%

    No Known Activations