© 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. 223419
    Prev
    Next
    INDEX
    Explanations

    as funding

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

    AI adoption and regulation

    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
     rapidamente
    0.58
    rüstung
    0.55
    كامل
    0.53
     preparação
    0.53
    苌
    0.52
    叅
    0.52
    욀
    0.52
    کھوں
    0.52
    प्तान
    0.51
    ｵ
    0.49
    POSITIVE LOGITS
     to
    0.56
    0.53
    yo
    0.51
     likely
    0.49
     permissible
    0.47
    &
    0.47
    ↵↵
    0.46
    ringle
    0.46
     surrounding
    0.45
     permitted
    0.44
    Activations Density 0.002%

    No Known Activations