© 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. 2930
    Prev
    Next
    INDEX
    Explanations

    models disappearing

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

    unorthodox new combinations

    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
    古い
    0.47
    ೬
    0.45
     Европей
    0.45
    })$.
    0.45
    ти
    0.45
    䔉
    0.44
    ☺
    0.43
    ૨
    0.43
    젼
    0.43
     रामचंद्र
    0.43
    POSITIVE LOGITS
     unprecedented
    0.54
     reimag
    0.52
     Fintech
    0.52
     alongside
    0.51
     curated
    0.50
     –
    0.50
     seamlessly
    0.50
     fintech
    0.49
     parceria
    0.47
     with
    0.47
    Activations Density 0.019%

    No Known Activations