© 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. 37722
    Prev
    Next
    INDEX
    Explanations

    alternative code branches

    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
     thậm
    -0.82
     or
    -0.82
     irrespective
    -0.80
    Weld
    -0.78
    のち
    -0.76
     JSONArray
    -0.75
     similares
    -0.72
    apj
    -0.72
     pouvez
    -0.71
    ofollow
    -0.71
    POSITIVE LOGITS
     other
    1.66
     otherwise
    1.61
     any
    1.44
     another
    1.25
    any
    1.20
    อื่น
    1.14
     autres
    1.09
     अन्य
    1.09
     دیگری
    1.08
     다른
    1.05
    Activations Density 0.011%

    No Known Activations