© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 6266
    Prev
    Next
    INDEX
    Explanations

    xanthan gum or xcdroast

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

    `xclip`, `xprop`, `dg`, `org`, `args`

    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_53_width_65k_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
    PSON
    0.48
    Кли
    0.43
    rogenic
    0.42
    بلی
    0.41
     숨
    0.41
    ியோ
    0.40
    вена
    0.40
    БО
    0.39
     reckon
    0.39
     ლ
    0.39
    POSITIVE LOGITS
     fra
    0.42
     frail
    0.39
    frac
    0.37
    color
    0.37
    将其
    0.37
    牫
    0.37
     frag
    0.37
    FrameID
    0.36
    andra
    0.36
    epers
    0.36
    Activations Density 0.004%

    No Known Activations