© 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. 115786
    Prev
    Next
    INDEX
    Explanations

    dental panels

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

    explaining or inquiring

    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
     scrivere
    0.53
     lap
    0.51
    erde
    0.51
     escrita
    0.50
     schreiben
    0.50
    ])$
    0.48
     fach
    0.47
    əsi
    0.46
     nörd
    0.46
     писать
    0.45
    POSITIVE LOGITS
    panels
    0.48
    Dental
    0.47
     Ammonia
    0.47
     नाटक
    0.46
    concent
    0.45
    シップ
    0.44
     Theatre
    0.44
    ابت
    0.44
    ཉ
    0.43
    த்துள்
    0.43
    Activations Density 0.000%

    No Known Activations