© 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. 12895
    Prev
    Next
    INDEX
    Explanations

    processing records and threads

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

    computational terms and code snippets

    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
    ﺔ
    0.48
    戕
    0.45
     полити
    0.44
     TRANSPORTURI
    0.44
    אי
    0.44
    ੯
    0.43
    미
    0.43
    谄
    0.43
    𝚐
    0.42
    𝘔
    0.42
    POSITIVE LOGITS
     calculate
    0.45
     had
    0.41
     final
    0.41
     result
    0.41
     achieve
    0.41
     last
    0.40
     self
    0.40
     returned
    0.40
     reactor
    0.39
     output
    0.38
    Activations Density 0.001%

    No Known Activations