© 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. 38312
    Prev
    Next
    INDEX
    Explanations

    recommendations and positive experiences

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

    sporty grace

    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
    :
    0.36
    这里的
    0.35
    ,
    0.34
    О
    0.34
    ↵↵↵↵
    0.33
     여러분
    0.33
    ที่คุณ
    0.33
    Bathroom
    0.32
     Photon
    0.32
    ،
    0.32
    POSITIVE LOGITS
     oxen
    0.40
     ತಯ
    0.40
     barrios
    0.38
     kangaroos
    0.38
     mydict
    0.38
     ghar
    0.37
     cnv
    0.37
    ccgi
    0.37
     ganglions
    0.36
     acrob
    0.36
    Activations Density 0.017%

    No Known Activations