© 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. 49845
    Prev
    Next
    INDEX
    Explanations

    spacing for wall ties

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

    predicting or serving a function

    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
    𝐅
    0.55
     seabed
    0.51
     legalized
    0.50
    טל
    0.49
    NSMutableArray
    0.46
    𝐦
    0.45
     gambler
    0.45
     legality
    0.44
    ტი
    0.44
     exchange
    0.44
    POSITIVE LOGITS
     There
    0.51
    ↵↵
    0.50
     Perform
    0.48
     McN
    0.46
    <start_of_image>
    0.46
     Its
    0.45
     Roboto
    0.45
     Drawings
    0.44
     Sketch
    0.44
     Lodge
    0.44
    Activations Density 0.000%

    No Known Activations