© 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. 60589
    Prev
    Next
    INDEX
    Explanations

    repeated 4

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

    early, release, target, firm

    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
    Keller
    0.47
    變
    0.46
    Cake
    0.46
    getCell
    0.45
    리와
    0.44
     Grants
    0.44
     விஜ
    0.43
    Ша
    0.42
    τα
    0.41
    по
    0.41
    POSITIVE LOGITS
     tof
    0.52
     nonzero
    0.50
     shin
    0.50
    ফট
    0.49
     supremum
    0.49
    ⿳
    0.49
     countertop
    0.49
     spectrogram
    0.47
     ().
    0.47
     vox
    0.47
    Activations Density 0.000%

    No Known Activations