© 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. 16300
    Prev
    Next
    INDEX
    Explanations

    English and cultural terms

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

    links containing us

    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
    ฤษ
    0.43
    英文
    0.41
    espèces
    0.39
    ইংরেজি
    0.39
    赝
    0.38
     يستخدم
    0.38
     খেলার
    0.38
    途径
    0.38
    ందూ
    0.37
    矸
    0.37
    POSITIVE LOGITS
     cuisine
    0.40
     kültür
    0.39
    laat
    0.39
     Quebec
    0.37
     cultural
    0.37
     Universität
    0.37
     Mathematic
    0.37
     kultur
    0.37
     Centrale
    0.36
    )/(
    0.36
    Activations Density 0.023%

    No Known Activations