© 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. 185112
    Prev
    Next
    INDEX
    Explanations

    introducing or describing subsequent actions

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

    africa, Europe, Divine Feminine

    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
    Negative Logits
    л
    0.62
    мий
    0.46
    炀
    0.46
     будь
    0.45
    ก
    0.44
     Abdullah
    0.42
    сий
    0.42
    ెం
    0.42
    瑭
    0.42
     जरूर
    0.42
    POSITIVE LOGITS
     ampio
    0.46
     pulsation
    0.46
     photometry
    0.46
     autre
    0.45
    ابی
    0.45
    Techn
    0.44
     direttamente
    0.44
    </h3>
    0.44
     formazione
    0.43
     adduct
    0.43
    Activations Density 0.000%

    No Known Activations