© 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. 39313
    Prev
    Next
    INDEX
    Explanations

    type declarations Go struct string int

    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
     a
    -2.06
     ouvrage
    -1.64
     médaille
    -1.50
     brinde
    -1.48
     épisode
    -1.46
     frère
    -1.45
     ilumina
    -1.45
     servido
    -1.42
    Avec
    -1.41
     rique
    -1.40
    POSITIVE LOGITS
    ↵↵
    2.36
    ↵
    1.73
     эту
    1.49
    越高
    1.43
     это
    1.40
     этих
    1.35
    ℅
    1.32
     этим
    1.30
    }$
    1.30
    </td>
    1.30
    Activations Density 0.022%

    No Known Activations