© 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. 124171
    Prev
    Next
    INDEX
    Explanations

    seeking help or expressing confusion

    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
     originalen
    -1.48
     (
    -1.42
    </td>
    -1.34
    seln
    -1.34
    orologio
    -1.29
    heft
    -1.27
    </em>
    -1.24
    considerable
    -1.23
     Idee
    -1.22
     geven
    -1.21
    POSITIVE LOGITS
    4
    1.64
    5
    1.59
     their
    1.44
     especta
    1.42
     couldn
    1.40
    8
    1.39
    少しでも
    1.35
     one
    1.33
     will
    1.33
    饜
    1.32
    Activations Density 0.136%

    No Known Activations