© 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. 95236
    Prev
    Next
    INDEX
    Explanations

    gift, present, service, find

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

    instructions, code, or specific terms

    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
    män
    0.51
     diamant
    0.49
     водо
    0.48
     marines
    0.48
     कुलकर्णी
    0.48
     vanligt
    0.47
    禱
    0.47
     вариан
    0.46
     pantai
    0.46
     रहता
    0.45
    POSITIVE LOGITS
    ][%
    0.48
     Năm
    0.47
    {[
    0.47
    traded
    0.46
    頑張
    0.46
    同志
    0.45
    broken
    0.45
    ](/
    0.45
     الميلاد
    0.44
    Dataset
    0.44
    Activations Density 0.001%

    No Known Activations