© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 87259
    Prev
    Next
    INDEX
    Explanations

    used to describe businesses

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

    contrasting point

    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
    ิล
    0.43
    만에
    0.42
     necessities
    0.42
    ıya
    0.42
    ل
    0.41
     conventions
    0.40
    드로
    0.40
    ਡ
    0.40
    ド
    0.39
     complexities
    0.39
    POSITIVE LOGITS
     आग
    0.50
     मिलता
    0.48
    ^{\#}\
    0.48
     dikatakan
    0.48
    ต่ำ
    0.48
     உயர்ந்த
    0.47
     ब्राह
    0.47
    \}}\
    0.46
     ट्रे
    0.46
     ተ
    0.46
    Activations Density 0.000%

    No Known Activations