© 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. 82871
    Prev
    Next
    INDEX
    Explanations

    following word prediction

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

    how to level things

    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
    Okno
    0.57
    应用
    0.53
    Mapa
    0.52
    地图
    0.51
    攻击
    0.51
    Sparse
    0.49
    Archivo
    0.49
    伪
    0.48
    Attack
    0.48
    IKV
    0.46
    POSITIVE LOGITS
    ren
    0.51
     endocr
    0.46
     duties
    0.45
     répon
    0.44
     endearing
    0.44
    imely
    0.44
    drig
    0.43
     enam
    0.43
     proprietors
    0.43
     headwinds
    0.43
    Activations Density 0.000%

    No Known Activations