© 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. 9669
    Prev
    Next
    INDEX
    Explanations

    coordinates and measurements

    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
     Therefore
    -1.65
    Discografia
    -1.45
    琹
    -1.45
     museo
    -1.41
    𓆟
    -1.36
    These
    -1.35
     caricatura
    -1.34
     그리고
    -1.33
     당신
    -1.32
     Gesetze
    -1.30
    POSITIVE LOGITS
     totalidad
    1.34
    sach
    1.29
     to
    1.27
     той
    1.26
    +}$
    1.23
     tuturor
    1.16
     capaces
    1.13
    still
    1.10
    cooper
    1.10
     still
    1.09
    Activations Density 0.352%

    No Known Activations