© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 4955
    Prev
    Next
    INDEX
    Explanations

    integer type assignments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <0xB4>
    0.72
     Davis
    0.68
    绶
    0.67
     धवन
    0.67
     gax
    0.64
    adri
    0.64
    騇
    0.64
     Bxa
    0.63
     कॉस
    0.62
    핌
    0.62
    POSITIVE LOGITS
     int
    4.13
    Int
    4.11
    int
    4.07
     Int
    3.99
     integer
    3.96
    INT
    3.82
    Integer
    3.67
     Integer
    3.64
     INT
    3.58
    integer
    3.56
    Activations Density 0.921%

    No Known Activations