© 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. 34-GEMMASCOPE-RES-131K
    7. 81022
    Prev
    Next
    INDEX
    Explanations

    association with

    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
    Anybody
    -1.70
    Everybody
    -1.38
    Though
    -1.38
    Somebody
    -1.33
    though
    -1.31
     anybody
    -1.27
    Thankfully
    -1.26
     Anybody
    -1.24
     acknowledgement
    -1.21
    somebody
    -1.21
    POSITIVE LOGITS
     with
    1.17
     in
    1.17
     ​​
    1.12
     XNUMX
    1.09
     !!
    1.09
     even
    1.06
     from
    1.03
     analyzes
    1.01
     !!!
    0.98
     always
    0.96
    Activations Density 0.025%

    No Known Activations