© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86141
    Prev
    Next
    INDEX
    Explanations

    technical concepts and entities

    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
    }^\
    -1.28
    Frankreich
    -1.24
     augen
    -1.24
     możemy
    -1.22
     Francus
    -1.22
    tetlen
    -1.21
     contextLoads
    -1.20
     abbiamo
    -1.17
     equally
    -1.17
     extremely
    -1.16
    POSITIVE LOGITS
     in
    1.45
    ᛉ
    1.23
     get
    1.23
     here
    1.22
     other
    1.21
     снимка
    1.11
    ologists
    1.10
     so
    1.09
     during
    1.09
     живот
    1.07
    Activations Density 0.354%

    No Known Activations