© 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. 107144
    Prev
    Next
    INDEX
    Explanations

    in locations, settings, or situations

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

    in a location

    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
    லம்
    0.47
    コンビニ
    0.47
    门口
    0.46
    }^{+}+\
    0.45
    脑袋
    0.44
     함수의
    0.44
    房間
    0.44
    یثیت
    0.43
     नदियों
    0.43
     पाण्या
    0.43
    POSITIVE LOGITS
     the
    0.57
     an
    0.57
     quintessential
    0.48
     praised
    0.46
     a
    0.45
    build
    0.44
     sector
    0.44
     lauded
    0.44
     Sector
    0.43
    volving
    0.43
    Activations Density 0.046%

    No Known Activations