© 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. 243489
    Prev
    Next
    INDEX
    Explanations

    barrels per day, success, or

    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
    含ま
    0.46
    كام
    0.45
     nerve
    0.43
    ام
    0.40
     Reed
    0.40
    Ч
    0.40
    ěl
    0.40
     $/
    0.40
     ricerc
    0.39
    Reed
    0.39
    POSITIVE LOGITS
     Kyushu
    0.55
     peas
    0.54
    imde
    0.52
    ܘ
    0.49
    rhinoceros
    0.48
     Guangdong
    0.48
    ଏ
    0.46
     ಕಟ್ಟ
    0.46
    rabbit
    0.46
    orderby
    0.46
    Activations Density 0.001%

    No Known Activations