© 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. 79434
    Prev
    Next
    INDEX
    Explanations

    your breakfast

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

    time of day

    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
     நகா
    0.51
    epik
    0.46
     সালফেট
    0.45
    нология
    0.44
    𝗢
    0.44
    今回の
    0.44
    𝐁
    0.44
    uç
    0.43
    WINDOW
    0.42
    ananti
    0.42
    POSITIVE LOGITS
     as
    0.45
     recklessly
    0.44
     son
    0.43
     eg
    0.43
     persist
    0.41
     fearful
    0.41
     carelessly
    0.41
    드를
    0.41
     não
    0.40
     ply
    0.40
    Activations Density 0.000%

    No Known Activations