© 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. 48631
    Prev
    Next
    INDEX
    Explanations

    earned years made status paid won senses website nights

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

    biological, anatomical, and technical 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
    我
    0.51
    मैं
    0.50
     свои
    0.50
     мои
    0.49
    Ich
    0.46
     మేము
    0.45
    আমার
    0.45
     你
    0.44
    আমাকে
    0.42
     હું
    0.42
    POSITIVE LOGITS
     oneself
    0.79
     można
    0.48
     galima
    0.45
     можна
    0.44
    方は
    0.44
    มีการ
    0.44
     букмекерлар
    0.43
     jednom
    0.42
    場合の
    0.41
    atorul
    0.41
    Activations Density 0.228%

    No Known Activations