© 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. 10-GEMMASCOPE-RES-131K
    4. 11933
    Prev
    Next
    INDEX
    Explanations

    zero or null initialization

    np_acts-logits-general · gemini-2.5-flash-lite

    null values and initializations to zero or empty in programming code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     algunas
    -1.45
     your
    -1.41
    /*
    -1.38
     tendrás
    -1.34
     otras
    -1.27
     témo
    -1.27
     цена
    -1.27
     młod
    -1.26
     /*
    -1.25
    zema
    -1.25
    POSITIVE LOGITS
     for
    2.11
     when
    1.66
     new
    1.38
     one
    1.38
     because
    1.36
     as
    1.35
     and
    1.31
     same
    1.29
     in
    1.27
     their
    1.24
    Activations Density 0.022%

    No Known Activations