© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 111280
    Prev
    Next
    INDEX
    Explanations

    contextual phrases

    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
    ar
    0.53
     прошла
    0.49
    하면
    0.48
    。
    0.47
    первых
    0.47
     черный
    0.46
     первый
    0.46
    Universe
    0.46
    ।
    0.46
    EventType
    0.45
    POSITIVE LOGITS
     সক্ষম
    0.43
     estet
    0.41
     proxim
    0.41
     kib
    0.40
     presso
    0.40
     Louisville
    0.40
     überw
    0.40
     surg
    0.40
     sóng
    0.40
     realizzata
    0.39
    Activations Density 0.000%

    No Known Activations