© 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. 173250
    Prev
    Next
    INDEX
    Explanations

    products, brand new, values, water

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

    storing values, favors

    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
     자주
    0.51
     경제
    0.49
    躋
    0.49
     Frequently
    0.48
     ड्राइविंग
    0.47
    *
    0.47
     आर्थिक
    0.47
     이번
    0.46
    eless
    0.45
    uju
    0.45
    POSITIVE LOGITS
    我们要
    0.48
    گرم
    0.46
    рый
    0.46
     mne
    0.46
     you
    0.44
    扰
    0.44
     scribe
    0.44
     heals
    0.43
     horticultural
    0.43
    涧
    0.43
    Activations Density 0.001%

    No Known Activations