© 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. 136552
    Prev
    Next
    INDEX
    Explanations

    prepositions and connectors

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

    Rockefeller Center or Rock Observation

    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
    ه
    0.54
    ყ
    0.54
    ن
    0.54
     তন্ত্র
    0.49
     Fiberglass
    0.49
    ש
    0.48
    थ
    0.48
    ור
    0.48
     seiz
    0.48
     LAST
    0.48
    POSITIVE LOGITS
     pedestrian
    0.49
    ssh
    0.48
    '
    0.46
    lectual
    0.46
    essori
    0.44
    are
    0.43
    ihn
    0.43
    ledge
    0.43
    ges
    0.43
    ahn
    0.42
    Activations Density 0.000%

    No Known Activations