© 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. 71587
    Prev
    Next
    INDEX
    Explanations

    Sharing my story

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

    The neuron is primarily triggered by personal‐pronoun tokens (I, you, we, etc.), i.e. parts of the text that express a personal narrative or address.

    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
     capuche
    -1.24
     duur
    -1.12
     majd
    -1.10
    ној
    -1.09
     ندار
    -1.08
     (!__
    -1.03
    咁
    -1.03
     занятий
    -1.02
     alleen
    -1.01
     pudiera
    -1.01
    POSITIVE LOGITS
     my
    1.60
     I
    1.35
     tonight
    1.31
     tomorrow
    1.28
    noteq
    1.23
     nabíz
    1.22
     možná
    1.20
     pequenas
    1.19
     today
    1.17
     可能
    1.17
    Activations Density 0.019%

    No Known Activations