© 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. 129249
    Prev
    Next
    INDEX
    Explanations

    ID card

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

    specific words followed by context

    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
     or
    0.41
    lia
    0.41
     ።
    0.40
     또는
    0.39
    리아
    0.39
    Vecchio
    0.39
    または
    0.38
    ちなみに
    0.37
    ճ
    0.37
    ute
    0.36
    POSITIVE LOGITS
    槤
    0.42
     разнообраз
    0.40
    埸
    0.40
     लगाकर
    0.39
    ହା
    0.39
     দুপুরে
    0.37
    眽
    0.37
    8
    0.37
     quieras
    0.37
     sôi
    0.36
    Activations Density 0.000%

    No Known Activations