© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 83576
    Prev
    Next
    INDEX
    Explanations

    official. clergy and religious concepts

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

    dynamic processes

    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
    کو
    0.44
    .~\
    0.43
     mówi
    0.43
    Smartphone
    0.43
    对自己
    0.42
     stále
    0.42
    का
    0.41
     Naturally
    0.41
    ឆ្ល
    0.41
    Rights
    0.41
    POSITIVE LOGITS
    omed
    0.49
     cleric
    0.45
    um
    0.44
     palette
    0.44
     peacock
    0.43
    bucks
    0.43
    t
    0.42
    ोच्च
    0.41
     crane
    0.41
     cuento
    0.41
    Activations Density 0.000%

    No Known Activations