© 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-65K
    7. 27990
    Prev
    Next
    INDEX
    Explanations

    identifying healthy or shared resources

    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_65k_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
    0.47
     философия
    0.47
     famous
    0.44
     ҷ
    0.43
     ค่า
    0.42
    Philosophy
    0.42
     gratu
    0.42
     ê
    0.42
     टीच
    0.42
     বিশ্বে
    0.42
    POSITIVE LOGITS
    يت
    0.44
     oyn
    0.42
    adás
    0.41
    烷
    0.41
    瀝
    0.40
    izieren
    0.40
    deren
    0.39
    哆
    0.39
    縱
    0.39
    䝬
    0.39
    Activations Density 0.003%

    No Known Activations