© 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. 160574
    Prev
    Next
    INDEX
    Explanations

    Spinoza's Ethics and religion

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

    Dutch philosophy and economics

    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
     Enugu
    0.43
     Inns
    0.43
    THAN
    0.43
    mero
    0.43
    Merc
    0.42
     THAN
    0.42
    Inn
    0.42
    夸
    0.42
    ueling
    0.42
    근
    0.42
    POSITIVE LOGITS
     halogen
    0.44
     synagogue
    0.44
     halal
    0.42
     mortgages
    0.42
     Judaism
    0.41
     ejaculation
    0.40
     解
    0.40
    解
    0.40
     riots
    0.40
    varrho
    0.39
    Activations Density 0.006%

    No Known Activations