© 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. 3832
    Prev
    Next
    INDEX
    Explanations

    numbers and letters

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

    modelpretrained hardware model numbers

    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
     ఆర్థిక
    0.36
     финансо
    0.34
    퐫
    0.34
    碐
    0.33
    诏
    0.32
    覦
    0.32
    徭
    0.32
    चुअल
    0.32
    巉
    0.32
    飏
    0.32
    POSITIVE LOGITS
    0.43
    g
    0.41
    w
    0.40
    l
    0.39
    x
    0.39
    -
    0.38
    m
    0.38
    j
    0.37
    v
    0.37
    t
    0.37
    Activations Density 0.215%

    No Known Activations