© 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. 96165
    Prev
    Next
    INDEX
    Explanations

    this remarkable thing

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

    these descriptive adjective

    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
     subiect
    0.56
    គុ
    0.51
    觧
    0.47
     ควร
    0.46
    ಿಗಳು
    0.46
     jaaye
    0.46
     Defts
    0.46
    ക്കുറ
    0.46
    끝
    0.45
     sét
    0.44
    POSITIVE LOGITS
     enormes
    0.57
    ormous
    0.55
     огром
    0.55
     huge
    0.52
    すごい
    0.50
     огромное
    0.50
     enormous
    0.49
    すごく
    0.47
     incredible
    0.46
     amazing
    0.46
    Activations Density 0.053%

    No Known Activations