© 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. 30215
    Prev
    Next
    INDEX
    Explanations

    greek language and greece

    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
    лаб
    0.51
    来讲
    0.42
     일반
    0.41
     область
    0.40
    öffentlich
    0.39
    ป์
    0.39
     Koš
    0.39
    구
    0.38
     явля
    0.38
     එව
    0.38
    POSITIVE LOGITS
     στη
    0.55
    Ι
    0.55
    τε
    0.55
    να
    0.55
     σου
    0.54
    Σ
    0.54
     ο
    0.53
     τε
    0.53
    Τ
    0.53
     μου
    0.53
    Activations Density 0.004%

    No Known Activations