© 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. 19212
    Prev
    Next
    INDEX
    Explanations

    indoor, outdoor, and directional locations

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

    physical and digital locations

    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
     който
    0.54
     വീഡിയോ
    0.53
     което
    0.52
     тази
    0.52
     ্
    0.47
     此
    0.47
     когато
    0.47
     другие
    0.46
    に近い
    0.46
     ອ
    0.46
    POSITIVE LOGITS
    هم
    0.57
    .
    0.54
     with
    0.53
     the
    0.52
    کش
    0.50
    ifrån
    0.50
    seits
    0.48
     Palacio
    0.48
    ,
    0.46
    g
    0.45
    Activations Density 0.087%

    No Known Activations