© 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. 41827
    Prev
    Next
    INDEX
    Explanations

    reducing time

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

    time spent or it takes

    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
     היה
    0.50
    ५
    0.50
    ८
    0.50
    ؟
    0.49
    regardless
    0.49
    ри
    0.49
    ৫৮
    0.48
    5
    0.48
    ਨ
    0.48
     мм
    0.47
    POSITIVE LOGITS
     trauma
    0.51
     therapy
    0.50
     floss
    0.50
    療法
    0.50
     therapies
    0.50
     disrupts
    0.49
     disruption
    0.49
     Therap
    0.48
     remediation
    0.48
     disruptions
    0.47
    Activations Density 0.006%

    No Known Activations