© 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. 229201
    Prev
    Next
    INDEX
    Explanations

    specific breeds or types

    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
     maternelle
    0.50
     plasmas
    0.45
     differentiated
    0.44
    誓
    0.44
     plasma
    0.44
     remodeling
    0.44
     résolution
    0.43
    кие
    0.43
     différen
    0.42
     remod
    0.41
    POSITIVE LOGITS
     madeira
    0.54
    𝚐
    0.50
     其他
    0.48
     गिल
    0.48
    𝑔
    0.48
    𝒜
    0.48
    glyphs
    0.47
    extra
    0.46
    𝗠
    0.46
    elimin
    0.45
    Activations Density 0.001%

    No Known Activations