© 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. 114414
    Prev
    Next
    INDEX
    Explanations

    infrastructure or technology connections

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

    imagery

    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
     عورت
    0.48
    婊
    0.48
    navi
    0.45
     Arrang
    0.44
     모두
    0.43
    女性
    0.43
    座位
    0.42
     chuyện
    0.42
    깔
    0.42
    咧
    0.42
    POSITIVE LOGITS
     methane
    0.53
     hidro
    0.48
     зависит
    0.46
     HYDRO
    0.46
     trabajo
    0.43
     photochemical
    0.43
     suele
    0.43
    )}/>
    0.43
     lavoro
    0.42
     REPLACE
    0.42
    Activations Density 0.003%

    No Known Activations