© 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. 94857
    Prev
    Next
    INDEX
    Explanations

    locality, geographical features

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

    sharing local web server

    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
    ட்டு
    0.54
    URNIZ
    0.54
     Fehl
    0.54
     இந்த
    0.53
    Ꮸ
    0.53
     αυτή
    0.52
    垻
    0.52
     זה
    0.51
     الفعل
    0.51
    ことが
    0.51
    POSITIVE LOGITS
     locality
    0.42
    ivity
    0.41
     regardless
    0.40
    mapper
    0.40
    界
    0.39
    bou
    0.39
     nestled
    0.38
    lobe
    0.38
    arakat
    0.38
     races
    0.38
    Activations Density 0.001%

    No Known Activations