© 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. 1505
    Prev
    Next
    INDEX
    Explanations

    check house world open

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

    lyrics for Flashing Lights

    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
     glycoproteins
    0.44
     單
    0.37
     electrolytes
    0.36
     waveguide
    0.36
     nanofibers
    0.36
     RetValue
    0.36
     micelles
    0.35
     electrodes
    0.35
     manipulations
    0.35
     phospholipids
    0.35
    POSITIVE LOGITS
    if
    0.47
    <h2>
    0.46
    <h3>
    0.43
    www
    0.42
    p
    0.42
    this
    0.41
    get
    0.38
    What
    0.38
    home
    0.38
    tired
    0.37
    Activations Density 0.000%

    No Known Activations