© 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. 1270
    Prev
    Next
    INDEX
    Explanations

    Greek and related concepts

    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
    Religion
    0.42
    rivers
    0.41
    Gesch
    0.40
    缛
    0.39
    ashire
    0.39
    স্টি
    0.39
    നിയ
    0.39
     karit
    0.39
     河
    0.38
    녀
    0.38
    POSITIVE LOGITS
     system
    0.45
     CH
    0.44
     System
    0.41
     NOK
    0.40
     q
    0.40
     SYSTEM
    0.39
     CON
    0.38
     DAW
    0.38
     Q
    0.38
    空白
    0.38
    Activations Density 0.001%

    No Known Activations