© 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. 124
    Prev
    Next
    INDEX
    Explanations

    verb "have" followed by article or quantity

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

    having a/an/any/some

    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
     jeweiligen
    0.12
    ックス
    0.11
    ﭜ
    0.11
     vagy
    0.11
    \",
    0.11
     oppure
    0.11
     किंवा
    0.11
     अथवा
    0.10
    を見た
    0.10
    あるいは
    0.10
    POSITIVE LOGITS
     a
    0.24
     an
    0.19
     the
    0.18
     A
    0.16
     one
    0.16
     more
    0.15
     no
    0.15
     much
    0.14
     plenty
    0.14
     alot
    0.14
    Activations Density 0.771%

    No Known Activations