© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39064
    Prev
    Next
    INDEX
    Explanations

    console output

    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
     divertida
    -1.68
     belangrijke
    -1.55
     obtuvo
    -1.45
     entstanden
    -1.43
     animada
    -1.38
     办
    -1.33
     défaite
    -1.33
     einfachen
    -1.31
     insbesondere
    -1.30
     divertido
    -1.30
    POSITIVE LOGITS
     ecran
    1.61
     asado
    1.48
     fiscale
    1.41
     romero
    1.38
     ALEXANDER
    1.36
     افغانستان
    1.36
     zout
    1.34
     寿
    1.32
    ]$
    1.31
     zei
    1.31
    Activations Density 0.004%

    No Known Activations