© 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. 10-GEMMASCOPE-RES-131K
    7. 130123
    Prev
    Next
    INDEX
    Explanations

    eventual outcomes or consequences

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on occurrences of the word “eventual” (and its inflected form “eventually”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     If
    -2.58
     of
    -2.53
     is
    -2.25
     haste
    -2.16
     were
    -2.13
    絢
    -2.05
     In
    -2.05
     télévisée
    -2.02
    waniu
    -1.99
    太多的
    -1.98
    POSITIVE LOGITS
    樒
    2.89
    一旁的
    2.55
    ꪔ
    2.44
    鹇
    2.42
    一旁
    2.41
     sidan
    2.41
    钲
    2.38
     ideales
    2.38
    
    2.36
    ﹍﹍
    2.33
    Activations Density 0.001%

    No Known Activations