© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 95435
    Prev
    Next
    INDEX
    Explanations

    class declarations

    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
     rése
    -2.30
     inond
    -2.27
     célè
    -2.25
     plafon
    -2.19
     anún
    -2.17
     enthou
    -2.14
     maniere
    -2.13
    쐈
    -2.13
     peluche
    -2.11
     facilite
    -2.09
    POSITIVE LOGITS
    A
    2.66
    j
    2.44
    I
    2.44
    f
    2.41
    il
    2.39
    L
    2.33
    D
    2.28
    q
    2.22
    w
    2.17
    u
    2.14
    Activations Density 0.009%

    No Known Activations