© 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. 85661
    Prev
    Next
    INDEX
    Explanations

    collective experiences

    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
     you
    -1.81
     they
    -1.55
     is
    -1.52
     September
    -1.51
    ↵
    -1.47
    ”，
    -1.47
    铬
    -1.36
     Nacionales
    -1.34
     December
    -1.33
    overs
    -1.33
    POSITIVE LOGITS
    }^{+\
    1.34
     lastly
    1.31
     into
    1.29
    割合
    1.29
     consisted
    1.28
     spez
    1.27
    strona
    1.23
    Manufact
    1.22
     εικό
    1.21
    很久
    1.20
    Activations Density 0.040%

    No Known Activations