© 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. 97387
    Prev
    Next
    INDEX
    Explanations

    identity or origin

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

    "Fake" "site" "owning" "you"

    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
    meld
    0.44
     engage
    0.40
    ვი
    0.40
    val
    0.39
     ignore
    0.39
     ಕಳೆದ
    0.38
    随
    0.38
    v
    0.37
    min
    0.37
     Jupyter
    0.37
    POSITIVE LOGITS
     ስርዓ
    0.51
    Persona
    0.49
    董事长
    0.47
    Routed
    0.47
    antown
    0.47
    ട്ടി
    0.47
    Mission
    0.45
    Rite
    0.45
    𝖔
    0.45
    WriteHeader
    0.45
    Activations Density 0.001%

    No Known Activations