© 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. 216797
    Prev
    Next
    INDEX
    Explanations

    foreign language words

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

    future or uncertainty

    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
     أع
    0.41
    0.41
    <0x9D>
    0.40
     FRIEND
    0.38
     সমাজের
    0.38
     पहुंचकर
    0.38
     is
    0.37
     belonging
    0.37
     user
    0.36
     shared
    0.36
    POSITIVE LOGITS
     sezonie
    0.59
    archiw
    0.57
     Medizin
    0.55
     zmienia
    0.55
    ຜະລ
    0.53
    newsletter
    0.53
    敛
    0.52
     Wię
    0.52
     Ayurved
    0.51
     neke
    0.51
    Activations Density 0.001%

    No Known Activations