© 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. 229274
    Prev
    Next
    INDEX
    Explanations

    occupancy sensor

    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
    нда
    0.54
    👮
    0.54
    ду
    0.48
    အတွ
    0.46
    anner
    0.45
     கர
    0.45
     熱
    0.45
     Андрей
    0.44
    ેચ્છ
    0.44
     Саша
    0.43
    POSITIVE LOGITS
    h
    0.51
     conval
    0.50
     malignancy
    0.50
     সংক্রমণ
    0.49
     Tod
    0.47
     potencia
    0.46
     pathophysiology
    0.46
    ifiable
    0.46
     latitudine
    0.46
     concl
    0.44
    Activations Density 0.001%

    No Known Activations