© 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. 194603
    Prev
    Next
    INDEX
    Explanations

    numbers preceding specific professions

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

    often or usually followed by verbs

    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
    ...
    0.56
    ?
    0.54
    less
    0.48
    ‘
    0.47
    )
    0.46
    ians
    0.46
    ？
    0.45
    se
    0.44
    sequ
    0.43
    herence
    0.43
    POSITIVE LOGITS
     iniciando
    0.55
     настройки
    0.54
     एकड़
    0.52
     ENVIRONMENTAL
    0.52
     luisant
    0.52
     กี้
    0.52
     ubicado
    0.51
     ubicada
    0.51
     MANUFACT
    0.51
    innerApiCalls
    0.50
    Activations Density 0.001%

    No Known Activations