© 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. 93029
    Prev
    Next
    INDEX
    Explanations

    noun relationship with next word

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

    The neuron fires on words that carry prominent derivational suffixes denoting states, actions, or processes (e.g. –ance/-ence, –ion, –ment, –ing).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     to
    -1.66
    というか
    -1.20
     or
    -1.20
     beziehungs
    -1.19
    uspiel
    -1.18
     nueve
    -1.16
     靴
    -1.16
    /
    -1.15
    arschu
    -1.15
     beş
    -1.12
    POSITIVE LOGITS
     Frankrijk
    1.16
    子は
    1.15
    ፝
    1.09
     hırka
    1.09
     compét
    1.08
    是真的
    1.07
    iotensin
    1.07
    THEY
    1.07
     perca
    1.06
     کردن
    1.05
    Activations Density 0.150%

    No Known Activations