© 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. 20914
    Prev
    Next
    INDEX
    Explanations

    1+1+2

    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
     to
    -1.78
     that
    -1.63
     света
    -1.35
     now
    -1.34
     past
    -1.30
     کرت
    -1.29
     previous
    -1.23
     last
    -1.21
     been
    -1.19
    ússia
    -1.16
    POSITIVE LOGITS
     péché
    1.43
    Also
    1.43
    These
    1.42
    也
    1.41
    Once
    1.38
    你
    1.38
    Since
    1.37
    This
    1.37
     ติด
    1.37
    这些
    1.33
    Activations Density 0.035%

    No Known Activations