© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 48171
    Prev
    Next
    INDEX
    Explanations

    smart electronics or hardware building blocks

    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_31_width_65k_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
    athlete
    0.55
    ಿ
    0.46
    প্রে
    0.45
     athlete
    0.45
    தல்
    0.44
     conna
    0.44
    िकी
    0.44
     Faculté
    0.43
    সাব
    0.42
     REACTORS
    0.42
    POSITIVE LOGITS
    uras
    0.53
     групи
    0.48
    O
    0.44
     Smartphones
    0.43
     Pinterest
    0.42
    usti
    0.42
    Yahoo
    0.42
    Har
    0.41
    vidia
    0.41
     одина
    0.40
    Activations Density 0.002%

    No Known Activations