© 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. 197268
    Prev
    Next
    INDEX
    Explanations

    dining room

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

    attaching JavaScript event listeners

    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
    ንሽ
    0.49
    িদ
    0.47
     polluting
    0.46
     মমতা
    0.46
    жд
    0.45
     கடந்த
    0.44
    킁
    0.44
     invariants
    0.44
    घाटन
    0.44
     methylation
    0.44
    POSITIVE LOGITS
    ။
    0.49
    ವಾರು
    0.48
    zględ
    0.48
    ️
    0.46
    arrow
    0.46
    w
    0.46
     Jon
    0.46
     termos
    0.44
    ILI
    0.44
     rám
    0.44
    Activations Density 0.002%

    No Known Activations