© 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. 13757
    Prev
    Next
    INDEX
    Explanations

    what ... when

    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
     עם
    0.37
    ת
    0.36
    ็ค
    0.33
     המ
    0.32
    ה
    0.32
     બનાવ
    0.32
     אי
    0.31
    ਿਕ
    0.31
    惀
    0.31
     ל
    0.31
    POSITIVE LOGITS
     quando
    0.34
     ergonom
    0.32
     physiologically
    0.32
     when
    0.32
     pathophysiology
    0.31
     ketika
    0.31
     mammalian
    0.31
     intramolecular
    0.31
     intraper
    0.31
    $=
    0.30
    Activations Density 0.002%

    No Known Activations