© 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. 29749
    Prev
    Next
    INDEX
    Explanations

    CSS or CS versions

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

    CSS styling and appearance

    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
     aside
    0.43
    ეფ
    0.42
     ump
    0.42
     Khr
    0.41
    ীদ
    0.41
    (
    0.41
     Приступ
    0.40
    )<
    0.40
    silver
    0.39
    dismiss
    0.39
    POSITIVE LOGITS
     CSA
    0.55
    ódio
    0.48
     CSI
    0.46
     Css
    0.46
    𝗔
    0.45
     CSE
    0.44
    css
    0.44
     CSS
    0.44
     두
    0.42
    CSS
    0.42
    Activations Density 0.007%

    No Known Activations