© 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. 128959
    Prev
    Next
    INDEX
    Explanations

    const declarations (SYS, AF, int)

    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
    Przed
    -1.30
    Jumlah
    -1.24
    Pozdrawiam
    -1.24
    años
    -1.22
     Drž
    -1.21
    któ
    -1.20
     mikina
    -1.20
    bezpiecz
    -1.18
     brancas
    -1.14
    今月
    -1.14
    POSITIVE LOGITS
    s
    1.41
    k
    1.36
    d
    1.34
    z
    1.34
    w
    1.34
     These
    1.24
    h
    1.23
    ar
    1.23
     is
    1.23
    y
    1.20
    Activations Density 0.001%

    No Known Activations