© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 155249
    Prev
    Next
    INDEX
    Explanations

    Goals For

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

    Individual Right

    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
    ι
    0.46
    PTI
    0.44
    Equivalent
    0.44
    ين
    0.43
    ônio
    0.43
    ਗ
    0.43
    ிருந்து
    0.43
    णु
    0.43
    Products
    0.43
    اخت
    0.43
    POSITIVE LOGITS
    стам
    0.59
    橱
    0.54
     persona
    0.53
     Vocal
    0.49
     送料
    0.48
     vocals
    0.47
     Pastoral
    0.46
    の声
    0.46
     प्राथमिकता
    0.46
     Librarian
    0.45
    Activations Density 0.001%

    No Known Activations