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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 200425
    Prev
    Next
    INDEX
    Explanations

    sounds fun

    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_31_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
     här
    0.45
    \
    0.45
     Trat
    0.45
    স্পতি
    0.44
     resaltar
    0.42
     enfrent
    0.42
     Primero
    0.42
    uoso
    0.41
     señalar
    0.41
     localidad
    0.40
    POSITIVE LOGITS
     এবং
    0.39
    博物館
    0.39
     AND
    0.39
     և
    0.39
     వివా
    0.39
    এবং
    0.38
     until
    0.38
    不動
    0.38
     بۆ
    0.37
     เดียว
    0.37
    Activations Density 0.011%

    No Known Activations