© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 13210
    Prev
    Next
    INDEX
    Explanations

    placeholder curly braces

    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
    <bos>
    -1.51
     únicamente
    -1.40
     Če
    -1.39
    only
    -1.38
     siempre
    -1.31
    Suara
    -1.31
     Если
    -1.30
     They
    -1.27
    Răsp
    -1.27
     μια
    -1.27
    POSITIVE LOGITS
    ти
    1.58
     événement
    1.48
    \&
    1.46
     \&
    1.44
    },
    1.43
    很高
    1.37
     is
    1.34
    阖
    1.30
     vorüber
    1.25
    美国的
    1.25
    Activations Density 0.001%

    No Known Activations