© 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. 51559
    Prev
    Next
    INDEX
    Explanations

    prepared for delivery

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

    prepare, preparing, preparation

    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
     erythemat
    0.43
    Scoped
    0.41
    <strong>
    0.40
    My
    0.40
    l
    0.39
     della
    0.39
     doub
    0.39
     l
    0.38
    zPosition
    0.38
    少
    0.38
    POSITIVE LOGITS
     तैयारियां
    0.58
     தாய
    0.54
    preparing
    0.52
     preparar
    0.51
     hazırl
    0.50
     लिखना
    0.49
     તૈયાર
    0.49
     Prepare
    0.49
    prepare
    0.48
     Prepar
    0.48
    Activations Density 0.000%

    No Known Activations