© 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. 177339
    Prev
    Next
    INDEX
    Explanations

    digital information or data

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

    time point observation

    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
     spitting
    0.50
     retaliation
    0.49
    κια
    0.43
     firearm
    0.43
    μένες
    0.42
     traced
    0.41
    嬌
    0.41
     translators
    0.41
     queries
    0.40
    έν
    0.40
    POSITIVE LOGITS
     Mobility
    0.52
     Ambos
    0.47
     Peker
    0.46
    窥
    0.46
     اصلی
    0.46
    年纪
    0.45
    р
    0.45
    ä
    0.45
     Dans
    0.45
    说的
    0.45
    Activations Density 0.002%

    No Known Activations