© 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. 24528
    Prev
    Next
    INDEX
    Explanations

    regardless of conditions

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

    domain specific terms

    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
     seulement
    0.48
     Pu
    0.41
     olvides
    0.40
     ۳
    0.40
    يريا
    0.39
     soltanto
    0.38
     housewives
    0.37
     depende
    0.37
     minuto
    0.37
     wichtigsten
    0.36
    POSITIVE LOGITS
    无论是
    0.53
    要么
    0.53
    无论
    0.49
    不管是
    0.49
    不仅
    0.48
     (>
    0.46
    無論
    0.46
    现在
    0.46
     regardless
    0.46
    不论
    0.45
    Activations Density 0.000%

    No Known Activations