© 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. 48728
    Prev
    Next
    INDEX
    Explanations

    specific noun phrases

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

    Constipated

    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
    偌
    0.53
     പരി
    0.48
     Decorative
    0.47
    校园
    0.46
    㭋
    0.45
     രണ്ട്
    0.44
    Decorative
    0.44
    幔
    0.44
     आहे
    0.44
     온도
    0.44
    POSITIVE LOGITS
     placental
    0.48
     outbreaks
    0.45
    外出
    0.44
     prosecutions
    0.44
     slowest
    0.44
    に基づく
    0.44
    Результа
    0.43
     quickest
    0.43
     finest
    0.42
     mitigated
    0.42
    Activations Density 0.000%

    No Known Activations