© 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. 87198
    Prev
    Next
    INDEX
    Explanations

    common technical phrases

    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
    Tú
    -0.98
    Garten
    -0.96
    阶级
    -0.94
    Espa
    -0.91
    horario
    -0.89
    Haiti
    -0.88
    Economía
    -0.88
    Fá
    -0.86
    Oui
    -0.86
    Lina
    -0.85
    POSITIVE LOGITS
    operatorname
    0.85
    Ma
    0.84
    ly
    0.82
     vaste
    0.82
    arch
    0.80
    Mu
    0.79
    S
    0.78
    de
    0.77
    pub
    0.76
    D
    0.76
    Activations Density 0.147%

    No Known Activations