Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 1272
    Prev
    Next
    INDEX
    Explanations

    Eligible Apple cards

    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
    स्टेंस
    0.47
    akannya
    0.47
    opio
    0.46
    成
    0.46
    getLong
    0.44
     পার
    0.44
     mae
    0.44
    铉
    0.43
    כ
    0.43
     какой
    0.43
    POSITIVE LOGITS
     imasmim
    0.49
     counterbalance
    0.45
     Pemer
    0.45
     sabbam
    0.44
     atop
    0.44
    ahertz
    0.44
     झाल्यावर
    0.43
     im
    0.43
     शिर
    0.43
     inequality
    0.42
    Activations Density 0.001%

    No Known Activations