© 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. 20210
    Prev
    Next
    INDEX
    Explanations

    python class definitions

    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
     étui
    -2.34
     dezelve
    -2.08
    xvii
    -2.08
     alho
    -2.06
     écran
    -2.06
     meub
    -2.06
     ordinateur
    -2.03
     organisme
    -2.02
     douane
    -1.98
     abonnement
    -1.96
    POSITIVE LOGITS
    1
    2.86
    2
    2.56
    4
    2.39
    3
    2.38
    5
    2.36
    </h2>
    2.30
     or
    2.27
    9
    2.25
     may
    2.19
     could
    2.16
    Activations Density 0.023%

    No Known Activations