© 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. 248304
    Prev
    Next
    INDEX
    Explanations

    burial will follow in

    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
    裒
    0.45
    边界
    0.44
     সার্বভৌম
    0.44
    ସ୍
    0.43
    ্মী
    0.43
    
    0.43
    ចេ
    0.42
    噙
    0.42
    同一
    0.42
     রাখিয়া
    0.42
    POSITIVE LOGITS
    a
    0.55
    o
    0.54
    don
    0.53
    can
    0.48
    reflect
    0.47
    ↵
    0.47
    includes
    0.46
    or
    0.46
    it
    0.45
    called
    0.45
    Activations Density 0.001%

    No Known Activations