© 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. 7775
    Prev
    Next
    INDEX
    Explanations

    function calls and methods

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

    class and function declarations

    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
     soweit
    0.24
    ından
    0.21
    perhaps
    0.21
     größer
    0.21
     челове
    0.21
    สำคัญ
    0.21
    瞩
    0.21
     silber
    0.21
     நின்று
    0.20
     результа
    0.20
    POSITIVE LOGITS
     B
    0.27
     G
    0.27
     M
    0.26
     getAll
    0.25
     T
    0.24
     R
    0.23
    HomeScreen
    0.23
     errorMessage
    0.22
     HomeScreen
    0.22
     get
    0.21
    Activations Density 0.003%

    No Known Activations