© 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. 44703
    Prev
    Next
    INDEX
    Explanations

    use followed by library namespaces

    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
    ༀ
    -2.42
     joyería
    -2.13
    蟜
    -2.06
    蟶
    -2.06
    </h3>
    -2.05
    idlertid
    -2.00
     médic
    -1.98
     patate
    -1.97
     juſ
    -1.96
     activiteiten
    -1.95
    POSITIVE LOGITS
    {
    2.72
    </b>
    2.30
     There
    2.11
     in
    2.06
     not
    2.03
     need
    1.91
     at
    1.90
    ….”
    1.86
     that
    1.79
    广西
    1.79
    Activations Density 0.005%

    No Known Activations