© 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. 128094
    Prev
    Next
    INDEX
    Explanations

    UK Group, my abilities, murder of, Day of, dishes., afraid., widely used

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

    crime, crucial, nausea, famous, eager, getting

    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
    ۔
    0.54
    a
    0.53
    Orig
    0.50
     isKindOfClass
    0.48
     সভাপত
    0.46
     intramuscular
    0.45
    ὃ
    0.45
     соответствующие
    0.45
    s
    0.45
    different
    0.44
    POSITIVE LOGITS
     पेमेंट
    0.53
    hetto
    0.51
     Hoo
    0.51
    ধিক
    0.50
    heten
    0.48
    romes
    0.48
     Meth
    0.46
    琲
    0.46
    ik
    0.46
     populace
    0.46
    Activations Density 0.000%

    No Known Activations