© 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. 100333
    Prev
    Next
    INDEX
    Explanations

    equipment, instruments, drivers

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

    descriptive adjectives for materials or capabilities

    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
     मुठभे
    0.48
    Pixel
    0.44
    onTouch
    0.44
    헐
    0.44
     criminality
    0.43
    ensureEqual
    0.43
    Incident
    0.42
    ナナ
    0.42
    邻
    0.42
     этап
    0.41
    POSITIVE LOGITS
     Announcements
    0.49
    umos
    0.49
     spada
    0.48
     PAGE
    0.48
     Yearbook
    0.47
     Comments
    0.45
     Announcement
    0.44
     Dairy
    0.44
     fris
    0.44
     RIA
    0.44
    Activations Density 0.000%

    No Known Activations