© 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. 101180
    Prev
    Next
    INDEX
    Explanations

    different to

    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
     AGRIC
    -1.20
     coloration
    -1.14
     також
    -1.12
    ?
    -1.12
     frail
    -1.11
    Guia
    -1.06
     أيض
    -1.05
     valencia
    -1.05
     utilization
    -1.03
     גם
    -1.03
    POSITIVE LOGITS
     not
    1.30
    ൦
    1.24
     több
    1.18
    ISATION
    1.18
     they
    1.18
     Gdy
    1.16
    煕
    1.15
     Це
    1.14
    дитесь
    1.13
    oes
    1.09
    Activations Density 0.063%

    No Known Activations