© 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. 10559
    Prev
    Next
    INDEX
    Explanations

    other duties and responsibilities

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

    implementing solutions

    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
     이를
    0.38
    Izq
    0.37
    சம்
    0.36
    ИС
    0.35
    윤
    0.35
    இந்த
    0.34
    ガ
    0.34
    जा
    0.34
    หรับ
    0.34
    오
    0.34
    POSITIVE LOGITS
     zoom
    0.42
     Zoom
    0.40
     ergonomic
    0.39
     Granite
    0.39
     URLs
    0.38
     Gran
    0.38
     ergonom
    0.37
     Bluetooth
    0.37
     novels
    0.37
     grenade
    0.37
    Activations Density 0.006%

    No Known Activations