© 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. 209398
    Prev
    Next
    INDEX
    Explanations

    as to early childhood

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

    classification and comparison

    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
    Shuffle
    0.50
    щё
    0.48
    ั่ง
    0.48
    Order
    0.46
    鈍
    0.46
    стрее
    0.45
    쇤
    0.45
     ose
    0.45
    ”（
    0.45
    ﺭ
    0.45
    POSITIVE LOGITS
     patrim
    0.46
     Chirurg
    0.45
     Patrimonio
    0.45
     posteriorly
    0.45
     postnatal
    0.45
     alquiler
    0.44
    স্থলে
    0.43
     cockpit
    0.42
     ҷ
    0.42
     psychotherapy
    0.41
    Activations Density 0.000%

    No Known Activations