© 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. 66240
    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
    (
    -1.10
     we
    -1.02
     have
    -1.00
     mentioned
    -0.99
     of
    -0.98
     SSL
    -0.94
     thru
    -0.93
    ั้ง
    -0.90
     nai
    -0.90
    SSF
    -0.89
    POSITIVE LOGITS
    abá
    1.16
    Privacy
    1.06
    ⸼
    1.00
     infinitely
    1.00
     入っ
    0.99
    żeń
    0.99
    ㆁ
    0.97
    Sexo
    0.96
     éte
    0.96
    zyński
    0.95
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.