© 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. 15303
    Prev
    Next
    INDEX
    Explanations

    defining variables with let

    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
     stratég
    -1.59
     mikrofon
    -1.48
     keramik
    -1.45
     webu
    -1.41
     kabát
    -1.39
     kré
    -1.38
     mód
    -1.38
     dátum
    -1.34
    Forrás
    -1.31
     őket
    -1.30
    POSITIVE LOGITS
    C
    1.41
    Y
    1.41
     N
    1.35
     J
    1.35
    N
    1.34
     S
    1.27
    S
    1.23
    K
    1.22
    E
    1.21
    w
    1.20
    Activations Density 0.001%

    No Known Activations