© 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. 40015
    Prev
    Next
    INDEX
    Explanations

    not only / 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
    האם
    -1.05
     Granted
    -0.99
     Zutaten
    -0.98
     mencegah
    -0.98
    Bakgrunnsstoff
    -0.96
    uities
    -0.94
    šanas
    -0.93
    явление
    -0.92
    ingtones
    -0.92
    más
    -0.91
    POSITIVE LOGITS
     but
    1.59
     here
    1.23
     sondern
    1.09
     現在
    1.09
     μόνο
    1.07
     you
    1.05
     just
    1.02
     those
    1.01
     tylko
    1.00
     particular
    0.96
    Activations Density 0.018%

    No Known Activations