© 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. 141611
    Prev
    Next
    INDEX
    Explanations

    manual measurement

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

    specializing in

    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
    rer
    0.44
     assemblages
    0.44
    orter
    0.43
     }^{
    0.42
    orters
    0.42
    transpose
    0.41
     sensations
    0.41
    여러분
    0.41
    orte
    0.41
     interstitials
    0.41
    POSITIVE LOGITS
     potp
    0.47
     menyel
    0.46
     じゃ
    0.46
    Grilled
    0.46
     पहाड़ी
    0.44
     পারেনি
    0.43
     concealed
    0.43
     succès
    0.43
     ま
    0.43
     સમસ્યા
    0.42
    Activations Density 0.001%

    No Known Activations