© 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. 69040
    Prev
    Next
    INDEX
    Explanations

    is suitable for

    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
     never
    -0.91
     not
    -0.85
     acto
    -0.81
    Sympto
    -0.81
     simply
    -0.79
     doesn
    -0.78
     パ
    -0.77
    彥
    -0.76
    nă
    -0.75
     Более
    -0.75
    POSITIVE LOGITS
     зелё
    0.96
     новым
    0.96
    はこの
    0.93
     harán
    0.93
     зелены
    0.91
    应该
    0.90
    section
    0.88
    いかない
    0.87
    ymm
    0.85
     parlant
    0.85
    Activations Density 0.007%

    No Known Activations