© 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. 145851
    Prev
    Next
    INDEX
    Explanations

    future instructions

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

    into, of, and

    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
     病
    0.52
    硕
    0.49
    四
    0.46
     goals
    0.45
    联盟
    0.45
    嚏
    0.44
    金
    0.44
     remettre
    0.43
     Coupons
    0.43
    友
    0.43
    POSITIVE LOGITS
     booted
    0.46
     وہ
    0.42
     sown
    0.41
    我现在
    0.41
    ॥
    0.40
    وە
    0.40
     presión
    0.40
     устройств
    0.39
     \[
    0.39
     ඉතා
    0.38
    Activations Density 0.000%

    No Known Activations