© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86119
    Prev
    Next
    INDEX
    Explanations

    sequence final punctuation

    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_10/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
    耵
    -2.98
     patienter
    -2.41
     karton
    -2.39
     bascul
    -2.34
    蚰
    -2.33
    ſſen
    -2.28
    𝄆
    -2.28
     چهارم
    -2.19
     鸭
    -2.17
     Dokter
    -2.17
    POSITIVE LOGITS
     in
    2.72
     
    2.55
    …..
    2.47
    ：“
    2.39
     “
    2.36
    z
    2.28
    —“
    2.25
     enticing
    2.23
    se
    2.16
    …”
    2.14
    Activations Density 0.010%

    No Known Activations