© 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
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14348
    Prev
    Next
    INDEX
    Explanations

    digital electronics

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

    transgender, cisgender, nicotine, underwear

    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_16k_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
    M
    0.48
    T
    0.45
     Strength
    0.45
    german
    0.44
     Scandal
    0.44
     esempi
    0.43
    POI
    0.43
    UCK
    0.43
    alleg
    0.43
    ENT
    0.42
    POSITIVE LOGITS
     folyam
    0.53
    é
    0.49
     көп
    0.49
    нам
    0.48
     vált
    0.48
    ленным
    0.48
     élet
    0.48
     ორ
    0.48
     miesto
    0.48
     filles
    0.47
    Activations Density 0.005%

    No Known Activations