© 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. 168720
    Prev
    Next
    INDEX
    Explanations

    legal and financial issues

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

    internet culture

    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
     foi
    0.52
    or
    0.50
    姓名
    0.49
     Kung
    0.47
    ":
    0.47
    ${
    0.46
     skal
    0.46
     confianza
    0.46
    /*
    0.46
     kung
    0.45
    POSITIVE LOGITS
     expedited
    0.63
     irritated
    0.56
     expedite
    0.53
     incurring
    0.50
     outraged
    0.49
     유사
    0.48
     비슷한
    0.48
     inflating
    0.47
     infancy
    0.46
     infringing
    0.46
    Activations Density 0.000%

    No Known Activations