© 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. 14273
    Prev
    Next
    INDEX
    Explanations

    not just

    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
     rather
    -1.11
    rather
    -1.02
    BOTH
    -1.01
     både
    -0.95
    雖然
    -0.93
    albeit
    -0.92
    而不是
    -0.92
     hormigón
    -0.92
    虽然
    -0.91
    स्थ
    -0.91
    POSITIVE LOGITS
     just
    2.16
     merely
    1.88
     only
    1.85
     только
    1.67
     tylko
    1.53
     simplemente
    1.45
     simply
    1.41
     فقط
    1.40
     hanya
    1.38
     mere
    1.35
    Activations Density 0.037%

    No Known Activations