© 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. 154994
    Prev
    Next
    INDEX
    Explanations

    foreign language elements and specific phrases

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

    defining items or actions

    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
    training
    0.56
    加工
    0.49
     தொழில்நுட்ப
    0.47
    apoptotic
    0.46
    workout
    0.46
    overlap
    0.45
    oxide
    0.44
    ן
    0.44
    protein
    0.44
    MING
    0.44
    POSITIVE LOGITS
     Để
    0.48
     bás
    0.46
     cesse
    0.46
     frères
    0.46
     Bhag
    0.46
     Deux
    0.46
     Đảng
    0.45
     Desire
    0.45
     nécess
    0.44
     Bhar
    0.44
    Activations Density 0.001%

    No Known Activations