© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 144198
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    an
    1.11
     powied
    0.99
    ar
    0.95
    न
    0.94
     dichas
    0.92
    ர்
    0.91
    <0x93>
    0.91
    arın
    0.91
    h
    0.90
     společnosti
    0.89
    POSITIVE LOGITS
     aux
    1.32
     Auxiliary
    1.28
    Aux
    1.23
     auxiliary
    1.22
    AUX
    1.16
     Aux
    1.05
    ا
    1.05
    을
    0.97
    iliary
    0.96
    нда
    0.95
    Activations Density 0.002%

    No Known Activations