© 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. 244234
    Prev
    Next
    INDEX
    Explanations

    annual fashion, mom gifts, boat bow

    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
     કોઈપણ
    0.46
    ađ
    0.45
     긴
    0.45
    ሮችን
    0.45
    अगर
    0.45
    μού
    0.44
     Hasbro
    0.44
    괵
    0.43
    ître
    0.43
    腾讯
    0.43
    POSITIVE LOGITS
     saldo
    0.51
     encirc
    0.47
     erfolgte
    0.47
     resultó
    0.46
     intolerance
    0.45
     crescimento
    0.44
     pseudos
    0.43
     sucedió
    0.43
     dessert
    0.43
     beslut
    0.43
    Activations Density 0.002%

    No Known Activations