© 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. 182314
    Prev
    Next
    INDEX
    Explanations

    sentence beginnings or list separators

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

    explaining errors, communication, decisions

    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
    ständ
    0.55
    镓
    0.52
     shunt
    0.51
     设置
    0.48
    વવા
    0.48
     الكون
    0.48
     gill
    0.47
     sled
    0.47
     glide
    0.47
     gills
    0.46
    POSITIVE LOGITS
    ლებიც
    0.48
     uwagi
    0.46
    лось
    0.45
    icho
    0.45
    esz
    0.45
    ė
    0.45
    സിൽ
    0.44
    τ
    0.43
    Ӏо
    0.42
     changement
    0.42
    Activations Density 0.000%

    No Known Activations