© 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. 114791
    Prev
    Next
    INDEX
    Explanations

    of your choice

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

    possessive or personal pronouns

    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
    转化为
    0.40
    াড়াও
    0.39
    춰
    0.39
     இதனால்
    0.39
     সাই
    0.38
    adığı
    0.38
     Statist
    0.38
    热
    0.37
     चुनावों
    0.37
     воск
    0.37
    POSITIVE LOGITS
     workpiece
    0.56
     your
    0.51
     votre
    0.50
     caregiver
    0.46
     discer
    0.46
     person
    0.45
     شما
    0.45
     zásobníku
    0.45
    your
    0.45
     cowork
    0.45
    Activations Density 0.001%

    No Known Activations