© 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. 60530
    Prev
    Next
    INDEX
    Explanations

    bibliography entries and image files

    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
     that
    -1.24
    legende
    -1.20
    wachen
    -1.18
     melding
    -1.18
    פרס
    -1.16
     scandals
    -1.15
     sponges
    -1.09
    羧
    -1.09
    נית
    -1.08
    zinha
    -1.06
    POSITIVE LOGITS
    2
    1.79
    1
    1.62
     very
    1.47
     antworte
    1.39
     first
    1.38
     -
    1.37
     slight
    1.36
    <
    1.34
    Like
    1.32
     noticeable
    1.32
    Activations Density 0.155%

    No Known Activations