© 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. 252171
    Prev
    Next
    INDEX
    Explanations

    time. category. that face

    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
     worthless
    0.49
     savages
    0.48
     вам
    0.46
    oxych
    0.46
     norske
    0.45
    یش
    0.45
     폐
    0.44
    र्स
    0.44
     사용
    0.44
    arts
    0.44
    POSITIVE LOGITS
     Rede
    0.47
     Mull
    0.44
    CI
    0.42
    الحمد
    0.42
    Coast
    0.41
    BTW
    0.41
    﨑
    0.41
    ID
    0.41
    Remainder
    0.41
    🛣
    0.40
    Activations Density 0.002%

    No Known Activations