© 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. 43027
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Thron
    -1.28
     anún
    -1.26
     \
    -1.25
     nuov
    -1.15
     cervello
    -1.12
    سلحة
    -1.11
    三年
    -1.10
    臜
    -1.10
    archiwizowane
    -1.09
    zkę
    -1.07
    POSITIVE LOGITS
     matière
    1.20
    corollary
    1.09
     pohod
    1.07
    ⡪
    1.00
    Виды
    1.00
    2
    0.99
     arse
    0.96
     carcinogenic
    0.96
    orul
    0.96
     usher
    0.96
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.