© 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. 104524
    Prev
    Next
    INDEX
    Explanations

    so + verb or don't

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

    reading or loading files/data

    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
     tata
    0.49
     mW
    0.46
     Strat
    0.45
    C
    0.44
     maya
    0.42
     C
    0.42
    ارب
    0.41
    CFT
    0.41
     adenosine
    0.40
     Maintains
    0.40
    POSITIVE LOGITS
    ̐
    0.50
    AllCaps
    0.46
    odhana
    0.45
     полуо
    0.45
    ocrite
    0.45
    isure
    0.45
    半
    0.45
    nextToken
    0.44
    oddsidemargin
    0.44
     концу
    0.44
    Activations Density 0.001%

    No Known Activations