© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35393
    Prev
    Next
    INDEX
    Explanations

    introduces a contrast

    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
     also
    -1.01
     نیز
    -1.00
     också
    -0.98
     bhi
    -0.97
    撄
    -0.95
    也要
    -0.93
     tudi
    -0.86
     olika
    -0.85
    wurst
    -0.85
     también
    -0.84
    POSITIVE LOGITS
     however
    1.76
    倒是
    1.49
     though
    1.48
    However
    1.48
    If
    1.36
     зато
    1.33
     però
    1.30
     porém
    1.23
     would
    1.22
     if
    1.20
    Activations Density 0.043%

    No Known Activations