© 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. 221816
    Prev
    Next
    INDEX
    Explanations

    place names and units

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

    bar slightly

    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
     صنایع
    0.46
     Coleoptera
    0.45
    উত্তরঃ
    0.45
     Hệ
    0.43
     میلیارد
    0.43
     çalışan
    0.42
    病例
    0.42
    ꒪
    0.42
    λογία
    0.41
     轻
    0.41
    POSITIVE LOGITS
    twenty
    0.50
    boy
    0.49
    cats
    0.49
    cm
    0.49
    ca
    0.48
    months
    0.48
    uchte
    0.48
    kip
    0.48
    kem
    0.48
    cem
    0.47
    Activations Density 0.000%

    No Known Activations