© 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. 64821
    Prev
    Next
    INDEX
    Explanations

    Benefits and professional roles

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

    criteria and successful actions

    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
    焔
    0.45
    系数
    0.45
     confusing
    0.44
     Measured
    0.44
    。
    0.44
     Rồi
    0.42
     kadın
    0.42
     femei
    0.42
     elecciones
    0.41
    他说
    0.41
    POSITIVE LOGITS
    ol
    0.48
    skateboard
    0.46
    Benefits
    0.46
    u
    0.44
    Bois
    0.43
    astas
    0.43
    Blog
    0.43
    crt
    0.43
     प्रभावशाली
    0.43
    in
    0.42
    Activations Density 0.000%

    No Known Activations