© 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. 12991
    Prev
    Next
    INDEX
    Explanations

    java package names

    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
     even
    -1.57
     not
    -1.53
     because
    -1.37
     undoubtedly
    -1.23
     despite
    -1.23
     tributo
    -1.18
     regardless
    -1.15
     their
    -1.14
    četně
    -1.14
     from
    -1.13
    POSITIVE LOGITS
    :"#
    1.21
    圌
    1.19
     ausein
    1.18
    摀
    1.17
     racines
    1.15
    wness
    1.13
    細かく
    1.10
    があり
    1.10
     grotte
    1.09
     procesos
    1.08
    Activations Density 0.007%

    No Known Activations