© 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. 208266
    Prev
    Next
    INDEX
    Explanations

    word followed by specific word

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

    self-improvement, CRM, internet slang, historical events

    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
     نقطه
    0.52
     دهد
    0.49
    㑒
    0.46
     წყ
    0.46
     mouvement
    0.46
     располага
    0.46
     Фе
    0.45
     কাশ
    0.45
     زیر
    0.45
     купить
    0.45
    POSITIVE LOGITS
    PR
    0.51
    locker
    0.47
    0
    0.47
    lip
    0.46
    ew
    0.46
    huge
    0.46
    alis
    0.46
    ate
    0.45
    high
    0.45
    ล็
    0.45
    Activations Density 0.001%

    No Known Activations