© 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. 53248
    Prev
    Next
    INDEX
    Explanations

    earlier in history

    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
    Ł
    0.48
     Session
    0.47
    Session
    0.47
     Sessions
    0.45
    ซี
    0.44
    紹
    0.43
     Messenger
    0.43
    Ça
    0.42
     brû
    0.42
    ELA
    0.42
    POSITIVE LOGITS
     представлены
    0.44
    uus
    0.42
    γων
    0.41
    ackbar
    0.40
    ௭
    0.40
    льності
    0.39
     hakim
    0.39
     cracks
    0.39
     menentukan
    0.38
     mutations
    0.37
    Activations Density 0.001%

    No Known Activations