© 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. 10-GEMMASCOPE-RES-131K
    7. 185
    Prev
    Next
    INDEX
    Explanations

    study

    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
     for
    -1.78
     there
    -1.77
     wśród
    -1.46
    chrift
    -1.44
     following
    -1.40
     which
    -1.38
    Now
    -1.38
     dilihat
    -1.37
     provide
    -1.36
     after
    -1.33
    POSITIVE LOGITS
    řízení
    1.45
    Ahol
    1.35
     tuoi
    1.35
    liegende
    1.34
    ",
    1.30
     verdaderas
    1.29
     แต่
    1.26
    誣
    1.26
     rám
    1.26
    Ee
    1.25
    Activations Density 0.206%

    No Known Activations