© 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. 7893
    Prev
    Next
    INDEX
    Explanations

    auto-incrementing serial numbers

    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
    ↵↵
    -1.96
     both
    -1.29
    …
    -1.26
    not
    -1.25
     FUCKING
    -1.24
     contents
    -1.21
    really
    -1.20
    把她
    -1.19
     contenant
    -1.19
     prova
    -1.16
    POSITIVE LOGITS
    lahir
    1.38
     mobilisation
    1.35
    していて
    1.35
    Dá
    1.33
    atalytic
    1.33
     memahami
    1.30
     expeditions
    1.28
    ྜ
    1.26
     memiliki
    1.25
     betaling
    1.23
    Activations Density 0.080%

    No Known Activations