© 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. 71305
    Prev
    Next
    INDEX
    Explanations

    production company descriptions

    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
     daily
    -1.01
    ﾐ
    -0.94
    全体
    -0.91
     even
    -0.89
    daily
    -0.86
    pyx
    -0.84
     jugo
    -0.83
    стный
    -0.82
     Change
    -0.82
     change
    -0.81
    POSITIVE LOGITS
     bisher
    1.41
     bislang
    1.18
    いくつか
    1.18
    今後も
    1.09
     exemplified
    1.09
     lately
    1.09
     examples
    1.08
     chaque
    1.07
    毎回
    1.06
    几次
    1.05
    Activations Density 0.144%

    No Known Activations