© 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. 73306
    Prev
    Next
    INDEX
    Explanations

    numbers and specific words

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

    bodies swap

    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
     opaque
    0.53
    实例化
    0.48
    ੁ
    0.46
     clearContext
    0.46
     conna
    0.46
     monochrome
    0.44
    书
    0.43
    较为
    0.43
     dense
    0.42
     monochromatic
    0.42
    POSITIVE LOGITS
    }=\
    0.59
    XXXX
    0.57
     YOUR
    0.55
     ½
    0.55
     YOU
    0.54
     FIVE
    0.54
    }=-
    0.53
     FOUR
    0.53
    4
    0.53
    YOUR
    0.52
    Activations Density 0.003%

    No Known Activations