© 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. 21420
    Prev
    Next
    INDEX
    Explanations

    NATO, alliances, security

    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
     Dernière
    -1.23
    Vlastnosti
    -1.20
     también
    -1.20
     Makanan
    -1.19
    only
    -1.18
     Descripción
    -1.14
     Commentaires
    -1.14
    ≻
    -1.13
     Manusia
    -1.12
     Fotografía
    -1.12
    POSITIVE LOGITS
     it
    1.29
     both
    1.13
     francisco
    1.07
     prostor
    1.07
    stas
    1.03
    staaten
    1.02
     οπο
    1.02
     "..\..\..\
    1.02
     predicates
    1.01
     ろ
    1.00
    Activations Density 0.032%

    No Known Activations