© 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. 242697
    Prev
    Next
    INDEX
    Explanations

    comparing different ages

    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
     Tomas
    0.47
     Carver
    0.46
     sayısı
    0.46
     looping
    0.46
     protests
    0.44
     pét
    0.44
    <unused85>
    0.44
     classes
    0.44
     intrigued
    0.44
     scored
    0.43
    POSITIVE LOGITS
    nienia
    0.47
    asibility
    0.44
    過
    0.44
    خدام
    0.44
     samband
    0.43
    лна
    0.42
    謊
    0.41
     आफ्नो
    0.41
    聳
    0.40
    าะ
    0.40
    Activations Density 0.000%

    No Known Activations