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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 75423
    Prev
    Next
    INDEX
    Explanations

    followed by with

    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
    With
    -1.89
    WITH
    -1.66
     WITH
    -1.36
     With
    -1.30
    with
    -1.24
    Avec
    -1.22
     Dengan
    -1.09
    與
    -1.07
    กับ
    -1.07
     avec
    -1.05
    POSITIVE LOGITS
     with
    0.97
    Kaynakça
    0.93
    有不少
    0.86
    pont
    0.82
    万円
    0.81
     ges
    0.78
     consid
    0.77
    w
    0.77
     conscience
    0.77
    をはじめ
    0.77
    Activations Density 0.166%

    No Known Activations