© 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. 43858
    Prev
    Next
    INDEX
    Explanations

    phrases or clauses

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

    Transformer, RPG, Terraform, country

    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
    вающий
    0.51
     рестора
    0.50
    ας
    0.50
    餐廳
    0.49
    một
    0.48
    ༣
    0.47
    하라
    0.46
    씻
    0.46
    dishwasher
    0.46
    peso
    0.46
    POSITIVE LOGITS
     the
    0.63
     Bram
    0.49
    ^{\
    0.46
     deepened
    0.46
     Mathematics
    0.45
     everything
    0.45
     performed
    0.44
     was
    0.44
     projects
    0.44
     Science
    0.44
    Activations Density 0.000%

    No Known Activations