© 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. 157541
    Prev
    Next
    INDEX
    Explanations

    titles and introductions

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

    violates safety guidelines

    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
     t
    0.50
     inlet
    0.48
     secretory
    0.48
     l
    0.45
     r
    0.45
     seco
    0.45
     inhalation
    0.44
     departe
    0.43
     ne
    0.43
     mandatory
    0.43
    POSITIVE LOGITS
    ৬
    0.52
    বিদ্য
    0.51
    इज
    0.51
    wrench
    0.47
     поддержа
    0.46
    を用
    0.45
     устра
    0.45
    ஔ
    0.44
    executions
    0.44
    infix
    0.44
    Activations Density 0.006%

    No Known Activations