© 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. 209295
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by nouns

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

    light and glow

    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
    HYDRO
    0.51
     फैलाने
    0.50
    輟
    0.49
    氢
    0.49
    iophene
    0.48
     HYDRO
    0.48
    icated
    0.47
     पुणे
    0.47
     वर्णन
    0.46
    imiter
    0.46
    POSITIVE LOGITS
    a
    0.45
    ters
    0.44
    <%=
    0.43
    Cabinet
    0.42
    Noto
    0.42
    incott
    0.42
    set
    0.42
    শে
    0.41
     Онлайн
    0.41
    ContextProvider
    0.41
    Activations Density 0.000%

    No Known Activations