© 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. 87932
    Prev
    Next
    INDEX
    Explanations

    OMG exclamation

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

    oh my god style exclamations

    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
     clase
    0.50
    army
    0.50
    antwoord
    0.50
     cosy
    0.49
    soldiers
    0.48
    狡
    0.48
    ir
    0.47
    uwe
    0.46
     melanch
    0.46
    ᱤ
    0.45
    POSITIVE LOGITS
     OMG
    0.75
    OMG
    0.66
     omg
    0.58
     WOW
    0.52
     Omaha
    0.48
     Ω
    0.48
    WOW
    0.48
    OMO
    0.47
    താ
    0.46
     Namibia
    0.46
    Activations Density 0.027%

    No Known Activations