© 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. 112286
    Prev
    Next
    INDEX
    Explanations

    traffic records, hair products, afford to

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

    holding longer

    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
    OUR
    0.55
    IX
    0.53
    SIX
    0.53
    熙
    0.52
    報酬
    0.52
    APE
    0.51
    Malaysia
    0.51
    Transforms
    0.50
    PRODUCTS
    0.49
    RE
    0.49
    POSITIVE LOGITS
    oprop
    0.52
    ‚
    0.50
    owal
    0.49
     wounds
    0.49
     expenditures
    0.47
    iejęt
    0.47
    ś
    0.47
    䇞
    0.47
     उदाहरण
    0.46
     चंदन
    0.46
    Activations Density 0.001%

    No Known Activations