© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 98601
    Prev
    Next
    INDEX
    Explanations

    pattern X followed by Y

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

    cashback, surveys, data entry

    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
     manca
    0.45
     MVP
    0.44
     OTC
    0.42
    anyag
    0.42
     Enquanto
    0.41
    although
    0.40
     팔
    0.40
     sola
    0.40
     pouze
    0.40
     thermoplastics
    0.39
    POSITIVE LOGITS
    ấy
    0.46
     Toán
    0.45
     sockaddr
    0.45
     UserName
    0.43
    も見
    0.43
    惩
    0.42
     ParkingLot
    0.40
    Inbox
    0.40
     explicación
    0.40
     ebenfalls
    0.39
    Activations Density 0.002%

    No Known Activations