© 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. 204523
    Prev
    Next
    INDEX
    Explanations

    cultivation of

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

    anointed with oil, infected rye

    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
    <unused282>
    0.46
     tume
    0.46
    ინი
    0.45
    <unused497>
    0.43
    BleStatus
    0.42
    CreationFailed
    0.42
     къ
    0.42
     ór
    0.42
    Abasis
    0.41
     którego
    0.41
    POSITIVE LOGITS
    CET
    0.46
    GPIO
    0.43
    덥
    0.43
     showcasing
    0.42
    Istituto
    0.42
    IFY
    0.42
    PON
    0.42
    সজ্জিত
    0.41
     হালকা
    0.40
    IOC
    0.40
    Activations Density 0.001%

    No Known Activations