© 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. 134429
    Prev
    Next
    INDEX
    Explanations

    common inanimate allergens from

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

    counting or measuring

    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
    ｇ
    0.44
    Цент
    0.42
    үр
    0.42
    ља
    0.41
    ۰
    0.40
     المركز
    0.40
    ર્મ
    0.40
     المزيد
    0.40
    RK
    0.39
    rawy
    0.39
    POSITIVE LOGITS
    streets
    0.44
    屢
    0.43
     nga
    0.42
     elev
    0.41
    Travelling
    0.41
     ng
    0.41
     electrolyte
    0.40
     m
    0.39
     পরীক্ষায়
    0.39
     streets
    0.39
    Activations Density 0.001%

    No Known Activations