© 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. 49546
    Prev
    Next
    INDEX
    Explanations

    city and state names

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

    locations followed by associated entities

    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
    🚇
    0.46
     비롯
    0.46
     Düsseldorf
    0.46
     कीमत
    0.46
    🗺
    0.45
     Київ
    0.45
    📮
    0.45
     Cologne
    0.44
     появления
    0.44
     cạnh
    0.44
    POSITIVE LOGITS
    Gn
    0.42
     Gn
    0.41
     magnis
    0.41
    ものを
    0.40
    Vt
    0.39
    मिथ
    0.39
     cirugía
    0.38
     pigment
    0.38
    Thickness
    0.38
    }//
    0.38
    Activations Density 0.019%

    No Known Activations