© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 119986
    Prev
    Next
    INDEX
    Explanations

    legal terms and concepts

    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
    ₃
    -1.35
    蛸
    -1.33
     også
    -1.33
     móvel
    -1.29
     following
    -1.29
    鯵
    -1.28
     houd
    -1.28
    turo
    -1.27
     hochzeit
    -1.27
     silber
    -1.27
    POSITIVE LOGITS
     not
    1.66
     they
    1.55
     I
    1.32
    ↵
    1.30
     nothing
    1.26
    </em>
    1.22
     i
    1.21
    1
    1.21
     F
    1.13
    rit
    1.13
    Activations Density 0.082%

    No Known Activations