© 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. 191958
    Prev
    Next
    INDEX
    Explanations

    Bill of Lading or conduct

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

    language tasks

    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
    दानी
    0.46
     Facebook
    0.45
     Populations
    0.45
     Campylobacter
    0.44
     Davao
    0.43
    :\/\/
    0.43
     infecciones
    0.43
     PubMed
    0.42
     Mycobacterium
    0.42
     Champion
    0.42
    POSITIVE LOGITS
    ቑ
    0.50
    ló
    0.49
     stirs
    0.48
     рассказа
    0.47
     accords
    0.47
     ро
    0.46
     со
    0.46
    geme
    0.44
    gow
    0.44
     الأمر
    0.44
    Activations Density 0.000%

    No Known Activations