© 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. 10-GEMMASCOPE-RES-131K
    7. 130402
    Prev
    Next
    INDEX
    Explanations

    turbocharged engines

    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
    凫
    -1.55
    pecabe
    -1.52
     навіть
    -1.41
    我又
    -1.40
    expiresIn
    -1.38
    Especificación
    -1.36
    dillas
    -1.34
     Aseg
    -1.34
    havior
    -1.32
     crowded
    -1.30
    POSITIVE LOGITS
    }
    1.91
    \
    1.88
    {
    1.46
     llenos
    1.45
    像
    1.34
    _{
    1.32
    }=
    1.32
    >
    1.31
    自分の
    1.26
    چند
    1.26
    Activations Density 0.008%

    No Known Activations