© 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. 174736
    Prev
    Next
    INDEX
    Explanations

    fuel level gauge

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

    future possibility/condition

    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
    o
    0.70
     Definitions
    0.54
     Skip
    0.53
     Lesson
    0.53
     Update
    0.52
     Workflow
    0.52
    isn
    0.52
    zień
    0.51
    op
    0.50
    oš
    0.50
    POSITIVE LOGITS
     antibodies
    0.64
     chlorides
    0.54
    応
    0.53
     antagonists
    0.52
     relatives
    0.51
     situs
    0.50
     colloidal
    0.50
     organelles
    0.50
     insects
    0.49
     pulsations
    0.49
    Activations Density 0.001%

    No Known Activations