© 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. 34-GEMMASCOPE-RES-131K
    4. 109218
    Prev
    Next
    INDEX
    Explanations

    paths and code references

    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_34/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
     and
    -2.13
     or
    -1.62
     supremely
    -1.38
     their
    -1.37
     this
    -1.36
     with
    -1.27
     enticing
    -1.24
    ⌗
    -1.23
     longstanding
    -1.16
     many
    -1.14
    POSITIVE LOGITS
    では
    1.55
    によって
    1.50
    を用
    1.41
    mainly
    1.38
    を使って
    1.38
    particularly
    1.37
    もある
    1.33
    がありますが
    1.32
    <bos>
    1.30
     桥
    1.28
    Activations Density 0.128%

    No Known Activations