© 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. 219269
    Prev
    Next
    INDEX
    Explanations

    foreign political entities and media

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

    interactive environment, attraction, voice assistant

    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
     ehemalige
    0.54
     çoğu
    0.51
     ngày
    0.49
    ને
    0.49
    邨
    0.49
     şark
    0.48
     ehemal
    0.48
    скет
    0.47
     miesięcy
    0.47
     amigo
    0.47
    POSITIVE LOGITS
    esting
    0.44
     Impacts
    0.42
    arks
    0.40
    㴬
    0.40
    rop
    0.39
    resh
    0.39
    oking
    0.39
    feedback
    0.39
     facilit
    0.39
     obscures
    0.39
    Activations Density 0.001%

    No Known Activations