© 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. 190
    Prev
    Next
    INDEX
    Explanations

    narrator role, Deadpool

    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
    </
    -1.33
     how
    -1.32
    </em>
    -1.18
    iseta
    -1.16
    łog
    -1.15
    Discus
    -1.07
     why
    -1.03
    </h4>
    -1.00
     Tiên
    -1.00
    ämp
    -1.00
    POSITIVE LOGITS
     leves
    1.25
    Turismo
    1.22
    BindingResult
    1.21
    alties
    1.19
     ὑ
    1.17
    ᕱ
    1.17
    licopter
    1.16
    ョン
    1.16
     wers
    1.16
    IATION
    1.16
    Activations Density 0.040%

    No Known Activations