© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 14304
    Prev
    Next
    INDEX
    Explanations

    going or heading somewhere

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stays
    0.48
     stay
    0.47
     יכול
    0.44
    stays
    0.44
     standstill
    0.43
    stay
    0.41
     lingered
    0.39
    ᔭ
    0.39
     приносит
    0.39
    最初
    0.38
    POSITIVE LOGITS
     berangkat
    1.15
    前往
    1.07
     headed
    1.02
     রওনা
    0.98
     heading
    0.97
    出发
    0.96
     रवाना
    0.93
    出発
    0.92
     출발
    0.85
     Heading
    0.84
    Activations Density 0.013%

    No Known Activations