© 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. 22-GEMMASCOPE-RES-131K
    7. 72621
    Prev
    Next
    INDEX
    Explanations

    related to activities and descriptions

    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_22/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
    3
    -1.57
     will
    -1.57
    4
    -1.55
    5
    -1.53
    0
    -1.50
     to
    -1.41
    2
    -1.38
    6
    -1.38
     being
    -1.38
    7
    -1.32
    POSITIVE LOGITS
     viſ
    1.39
     charmant
    1.35
     pittores
    1.32
     illustre
    1.30
     camion
    1.30
     moule
    1.27
     sés
    1.27
     serre
    1.27
     abonnement
    1.27
     savon
    1.27
    Activations Density 0.035%

    No Known Activations