© 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. 128063
    Prev
    Next
    INDEX
    Explanations

    Shouldly annotations or imports

    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
    länge
    -1.18
     kimdir
    -1.13
    sı
    -1.08
    ffiche
    -1.07
    はある
    -1.04
     новую
    -1.03
    frauen
    -1.02
     totalité
    -1.02
    çe
    -1.01
     céle
    -1.01
    POSITIVE LOGITS
    is
    1.27
    F
    1.20
    為に
    1.14
    IL
    1.13
    ii
    1.12
    Z
    1.10
     症
    1.10
    ack
    1.08
    B
    1.08
    as
    1.07
    Activations Density 0.001%

    No Known Activations