© 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. 173056
    Prev
    Next
    INDEX
    Explanations

    various concrete nouns

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

    included, international, wife, ethical

    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
     الف
    0.48
    కున్న
    0.48
    लया
    0.48
    屶
    0.47
     Velvet
    0.46
     Rach
    0.46
    餚
    0.46
     ہی
    0.46
     متجه
    0.46
     Ve
    0.46
    POSITIVE LOGITS
    0
    0.57
     fenders
    0.52
    (
    0.51
    0.50
    abu
    0.47
    za
    0.47
    viol
    0.47
     waterproof
    0.47
     protectors
    0.46
    Inspired
    0.46
    Activations Density 0.000%

    No Known Activations