© 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. 89872
    Prev
    Next
    INDEX
    Explanations

    residents, death, the, bring, on, downloader, against, ’s, faults

    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
    atl
    0.53
     شلون
    0.52
    av
    0.51
    ant
    0.49
    q
    0.47
     документ
    0.47
    ack
    0.46
    ag
    0.46
    quel
    0.46
    atak
    0.46
    POSITIVE LOGITS
     vases
    0.54
    ნება
    0.52
     spheres
    0.51
    
    0.51
     Ion
    0.49
     //.
    0.48
     laund
    0.48
     Arvind
    0.47
     umbrellas
    0.47
     Año
    0.47
    Activations Density 0.000%

    No Known Activations