© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 2642
    Prev
    Next
    INDEX
    Explanations

    multi-script and symbols

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

    technical terms and unicode

    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
    Not in Any Lists

    No Comments

    Negative Logits
     of
    0.58
     I
    0.56
     on
    0.54
     W
    0.53
     to
    0.50
    0.49
    .
    0.48
     A
    0.48
     K
    0.47
     Michael
    0.46
    POSITIVE LOGITS
     lateribus
    0.59
    ೇವಿನ
    0.57
    alaikums
    0.54
     GoObject
    0.54
    InfoPlistPath
    0.54
    円以上
    0.53
     longiore
    0.52
     phosphatase
    0.51
    ジネス
    0.51
     ڈپاز
    0.51
    Activations Density 0.000%

    No Known Activations