© 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. 251984
    Prev
    Next
    INDEX
    Explanations

    business transactions and their outcomes

    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
    decompose
    0.51
    無い
    0.48
    enson
    0.47
    )、
    0.47
     singlet
    0.47
     ポ
    0.46
    ósfera
    0.46
     ゴ
    0.44
    allergenic
    0.44
     سلسله
    0.44
    POSITIVE LOGITS
     produ
    0.47
     nav
    0.43
     arriver
    0.42
     produce
    0.41
     elegan
    0.41
     варто
    0.40
     tí
    0.40
     ass
    0.40
     oper
    0.40
    قف
    0.40
    Activations Density 0.000%

    No Known Activations