© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106791
    Prev
    Next
    INDEX
    Explanations

    technical defined terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     (!__
    -1.64
    if
    -1.46
    あー
    -1.34
     クリーム
    -1.26
     arbeitet
    -1.25
     najlepiej
    -1.24
     particolare
    -1.21
     migliorare
    -1.19
     gevonden
    -1.18
    //
    -1.17
    POSITIVE LOGITS
     (
    3.59
     abbreviated
    1.28
     páginas
    1.20
    简称
    1.17
     (“
    1.17
     $(\
    1.17
     Capítulo
    1.13
     prisa
    1.11
     siden
    1.11
     detal
    1.11
    Activations Density 1.052%

    No Known Activations