© 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. 34-GEMMASCOPE-RES-131K
    7. 117089
    Prev
    Next
    INDEX
    Explanations

    not X, but Y

    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_34/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
    However
    -1.53
     entanto
    -1.41
     kuitenkin
    -1.38
     jednak
    -1.36
    そして
    -1.31
     nevertheless
    -1.25
    それでも
    -1.22
    Однако
    -1.21
    しかし
    -1.19
    然而
    -1.16
    POSITIVE LOGITS
    而是
    3.55
     sondern
    3.14
     hanem
    2.17
     rather
    2.14
     nor
    2.13
     Rather
    1.97
     אלא
    1.91
     or
    1.90
     but
    1.84
    Rather
    1.79
    Activations Density 0.026%

    No Known Activations