© 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. 5996
    Prev
    Next
    INDEX
    Explanations

    GafferUI, Atheism

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

    Python code, code structures

    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
    त्रेयी
    0.28
    chyné
    0.28
    萩
    0.27
    OutgoingRiver
    0.27
     enkele
    0.27
     disponibilité
    0.26
     daarmee
    0.26
     textAppearance
    0.26
     siapa
    0.25
     chão
    0.25
    POSITIVE LOGITS
    ↵
    0.39
    ↵↵
    0.37
    0
    0.36
    4
    0.32
    5
    0.32
        
    0.32
    1
    0.31
    <0x0D>
    0.29
    при
    0.29
    2
    0.29
    Activations Density 0.327%

    No Known Activations