© 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. 80750
    Prev
    Next
    INDEX
    Explanations

    specific titles and entities

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

    aiding and abetting illegal acts

    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
     treinta
    0.49
    WIRE
    0.47
    iper
    0.47
     fós
    0.46
    sofar
    0.46
     छ
    0.46
    kräfte
    0.45
     Ш
    0.45
    нове
    0.45
    ists
    0.44
    POSITIVE LOGITS
    District
    0.46
     അനുവദ
    0.46
    Murder
    0.43
    Package
    0.43
     এখানকার
    0.42
    GraphQl
    0.41
    Afghan
    0.41
     menget
    0.41
     paket
    0.41
    Blocking
    0.41
    Activations Density 0.001%

    No Known Activations