© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44504
    Prev
    Next
    INDEX
    Explanations

    how to sell, add, buy

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

    This neuron fires on tokens carrying common English derivational or inflectional suffixes (-ed, ‑ied, ‑er, ‑ly, ‑s, ‑ation, ‑some, etc.).

    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
     $
    -1.66
     there
    -1.43
     weirdly
    -1.34
    𖣘
    -1.33
     beginnt
    -1.33
     his
    -1.32
     этого
    -1.31
    不需要
    -1.30
     at
    -1.28
     no
    -1.28
    POSITIVE LOGITS
     DETERMIN
    1.39
    یکر
    1.33
    鶫
    1.31
    甞
    1.30
     but
    1.28
     أثناء
    1.28
     blancs
    1.26
    踯
    1.24
     THEORY
    1.23
    萏
    1.23
    Activations Density 0.000%

    No Known Activations