© 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. 88178
    Prev
    Next
    INDEX
    Explanations

    death, chose, real, developed, cap

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

    business workflows and technical approaches

    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
    苻
    0.50
    ულ
    0.49
     ጥሩ
    0.47
     దర్శక
    0.46
    หลาย
    0.46
     또한
    0.46
    聂
    0.46
    栎
    0.46
    ադ
    0.45
     തന്റെ
    0.44
    POSITIVE LOGITS
    in
    0.49
     defraud
    0.45
     EMC
    0.45
     mesi
    0.44
     wartime
    0.44
     phased
    0.44
     planetary
    0.44
     impactos
    0.44
     efectiva
    0.43
     the
    0.42
    Activations Density 0.002%

    No Known Activations