© 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. 81085
    Prev
    Next
    INDEX
    Explanations

    Old City and surrounding areas

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

    non-English linguistic features

    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
     -
    0.52
    MAN
    0.51
     –
    0.50
    AN
    0.50
     RAN
    0.49
     ALEXANDER
    0.49
    RI
    0.48
     ...
    0.46
     PERFORMANCE
    0.46
     .
    0.46
    POSITIVE LOGITS
     новой
    0.50
    ọa
    0.46
     выпу
    0.45
    ర్చి
    0.45
     آج
    0.44
    饽
    0.44
    بعا
    0.43
    CubeSize
    0.42
    FormBorderStyle
    0.42
    يته
    0.42
    Activations Density 0.000%

    No Known Activations