© 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. 121991
    Prev
    Next
    INDEX
    Explanations

    preposition of

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

    issues, quantities, or specific entities

    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
    Police
    0.53
    ان
    0.52
    ツ
    0.51
    ال
    0.50
    டி
    0.50
    两
    0.49
    遊び
    0.49
    he
    0.48
    Part
    0.48
    Law
    0.48
    POSITIVE LOGITS
     tissus
    0.57
     drows
    0.56
     سبس
    0.56
     tkan
    0.52
     zásobníku
    0.52
     minerales
    0.51
     teatro
    0.51
     väik
    0.49
     міста
    0.48
     ಆತ್ಮ
    0.48
    Activations Density 0.000%

    No Known Activations