© 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. 188149
    Prev
    Next
    INDEX
    Explanations

    excellent great amazing

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

    Agents and APIs

    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
    '{
    0.50
    orm
    0.48
    ština
    0.48
     vertebral
    0.45
     ஸ்ட
    0.45
     {$
    0.44
     wetland
    0.43
     Mem
    0.43
     verte
    0.43
     appendix
    0.43
    POSITIVE LOGITS
    IFICATIONS
    0.51
    ین
    0.50
    یک
    0.50
    بین
    0.50
    痛み
    0.50
    ای
    0.50
     lelaki
    0.48
     عجیب
    0.48
    猷
    0.48
    ی
    0.47
    Activations Density 0.000%

    No Known Activations