© 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. 22-GEMMASCOPE-RES-131K
    7. 67090
    Prev
    Next
    INDEX
    Explanations

    or and / &

    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
    lihatan
    -1.32
     cadeaux
    -1.29
     diamants
    -1.28
     kabát
    -1.26
    لباس
    -1.24
    ünkü
    -1.23
     vernis
    -1.23
     abstrak
    -1.23
     nastro
    -1.22
     菇
    -1.21
    POSITIVE LOGITS
    d
    1.51
    r
    1.45
    v
    1.38
    u
    1.34
    ap
    1.34
    z
    1.34
    T
    1.33
    i
    1.32
    t
    1.30
    l
    1.30
    Activations Density 0.024%

    No Known Activations