© 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. 14026
    Prev
    Next
    INDEX
    Explanations

    unless, except, if

    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
     tantôt
    0.45
     halus
    0.45
     ?,
    0.42
     ogrom
    0.41
     รูป
    0.41
     található
    0.40
    mik
    0.40
     从
    0.39
     unimaginable
    0.39
    込め
    0.39
    POSITIVE LOGITS
     unless
    0.77
     except
    0.71
     якщо
    0.68
     אם
    0.68
    unless
    0.66
     if
    0.64
     если
    0.64
     যদি
    0.63
    যদি
    0.63
    если
    0.63
    Activations Density 0.055%

    No Known Activations