© 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. 99557
    Prev
    Next
    INDEX
    Explanations

    describing people or things

    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
     its
    -1.40
     and
    -1.31
     than
    -1.21
    \
    -1.16
     to
    -1.15
     värld
    -1.15
     that
    -1.14
     होगी
    -1.09
     suoi
    -1.08
    tigheter
    -1.07
    POSITIVE LOGITS
     ciclista
    1.28
     nôtre
    1.28
     musí
    1.24
     собі
    1.20
     cuillère
    1.17
    %).
    1.17
    　　《
    1.17
    migrationBuilder
    1.16
     sés
    1.16
     fibra
    1.15
    Activations Density 0.144%

    No Known Activations