© 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. 34-GEMMASCOPE-RES-131K
    7. 103613
    Prev
    Next
    INDEX
    Explanations

    award winning

    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_34/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
     environs
    -1.04
    Bereich
    -1.03
     tewas
    -0.98
     situations
    -0.94
     situazione
    -0.94
     situation
    -0.94
     diminutive
    -0.93
     bislang
    -0.90
     invariably
    -0.89
    こうした
    -0.89
    POSITIVE LOGITS
    热门
    0.91
    Παρα
    0.89
    TION
    0.89
     adap
    0.88
    〜〜
    0.88
    pentru
    0.88
    reihe
    0.84
    İN
    0.84
    casted
    0.84
    日报
    0.83
    Activations Density 0.061%

    No Known Activations