© 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. 24345
    Prev
    Next
    INDEX
    Explanations

    degrees and academic appointments

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

    numbers used as dates

    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
     ތ
    0.41
     incarnations
    0.41
     नवंबर
    0.40
    AF
    0.39
    संस्करण
    0.39
    -'
    0.38
     ສ
    0.37
     ГО
    0.37
     ស
    0.37
     October
    0.37
    POSITIVE LOGITS
    ูด
    0.47
     giocatore
    0.45
     मंत्र
    0.45
    ட்டால்
    0.45
    ším
    0.44
    <bbox>
    0.43
    Giá
    0.42
     förm
    0.42
     giọng
    0.42
    şı
    0.40
    Activations Density 0.014%

    No Known Activations