© 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. 36827
    Prev
    Next
    INDEX
    Explanations

    code structure delimiters

    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
     Folder
    0.48
     解
    0.41
     getText
    0.41
    Hemos
    0.40
     carpeta
    0.39
    𝘞
    0.38
    简历
    0.37
    ContextHeader
    0.37
    TakeVideo
    0.37
     भुव
    0.37
    POSITIVE LOGITS
     होईल
    0.41
    lepas
    0.40
    فرض
    0.39
     થશે
    0.38
    igious
    0.38
     একে
    0.38
    ګ
    0.38
    漬
    0.38
    araoh
    0.37
     ello
    0.37
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.