© 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. 23452
    Prev
    Next
    INDEX
    Explanations

    Jazz Fest or graft versus

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

    nullish coalescing, optional, coalesce, elvis operators

    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
    ları
    0.54
    u
    0.50
    ivores
    0.50
    clickView
    0.49
    ']['
    0.48
    }}-\
    0.48
     totalitarian
    0.48
    Titanic
    0.47
    funny
    0.47
     authoritarian
    0.46
    POSITIVE LOGITS
     knobs
    0.49
     Skull
    0.48
     knob
    0.45
    crs
    0.44
    溲
    0.44
    soff
    0.43
     Printers
    0.42
     Points
    0.42
     Seeking
    0.41
     City
    0.41
    Activations Density 0.000%

    No Known Activations