© 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. 83468
    Prev
    Next
    INDEX
    Explanations

    locational and descriptive phrases

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

    staffed by

    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
    hanti
    0.50
    после
    0.49
    
    0.49
     charla
    0.49
     cili
    0.48
     علیحد
    0.48
    Ạ
    0.47
    ilikom
    0.47
     суу
    0.47
     począ
    0.47
    POSITIVE LOGITS
     stars
    0.51
     retrieved
    0.42
    成
    0.42
     PB
    0.40
     *$
    0.40
     consumes
    0.40
     estrellas
    0.39
     GP
    0.39
    ेश्व
    0.39
     iterates
    0.38
    Activations Density 0.001%

    No Known Activations