© 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. 69833
    Prev
    Next
    INDEX
    Explanations

    quantity, time, sales

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

    reservations and bookings

    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
     be
    0.52
     birinci
    0.50
    neg
    0.49
    "+
    0.46
    studio
    0.46
    marker
    0.45
    乖
    0.44
     daerah
    0.43
     Antalya
    0.42
    ُ
    0.42
    POSITIVE LOGITS
     Colts
    0.46
    дят
    0.46
     médian
    0.46
     méd
    0.45
    因为它
    0.45
    よび
    0.45
    ስቃ
    0.45
     പക
    0.45
     গবেষণ
    0.44
    いる
    0.44
    Activations Density 0.001%

    No Known Activations