© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 82897
    Prev
    Next
    INDEX
    Explanations

    conditional clauses

    np_acts-logits-general · gemini-2.5-flash-lite

    two halves

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    লাষ
    0.47
     जाणार
    0.47
     жерт
    0.46
    졔
    0.46
     jednego
    0.46
    janja
    0.46
    coefficients
    0.44
    äfte
    0.44
     breezes
    0.44
    ᡳ
    0.44
    POSITIVE LOGITS
     إذا
    0.45
    Ό
    0.43
    Якщо
    0.42
     Nếu
    0.42
    如果
    0.41
     obvious
    0.41
    यदि
    0.40
     Patil
    0.40
    美国的
    0.40
    Για
    0.40
    Activations Density 0.001%

    No Known Activations