© 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. 28488
    Prev
    Next
    INDEX
    Explanations

    pub, Data, Charted, Algorithm, Blueprint

    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
    <h2>
    0.36
    <0xB3>
    0.35
     थ
    0.34
    Sn
    0.34
    υ
    0.34
    MainWindow
    0.33
     δ
    0.33
    <unused492>
    0.33
    <unused2117>
    0.33
    ι
    0.31
    POSITIVE LOGITS
     পূর্ববাংলা
    0.42
    ທີ່ມີ
    0.40
     নিঃসৃত
    0.39
     realises
    0.39
    řejmě
    0.39
     mistura
    0.39
     opcoes
    0.39
     esencia
    0.39
     किड्स
    0.39
     lekker
    0.38
    Activations Density 0.005%

    No Known Activations