© 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. 39961
    Prev
    Next
    INDEX
    Explanations

    personal states or feelings

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

    This neuron fires on first-person expressions of annoyance, displeasure, or puzzlement (e.g. “pisses me off,” “bothers me,” “puzzles me”).

    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
     for
    -1.30
     silencioso
    -1.07
     around
    -1.05
     on
    -1.04
     or
    -1.04
     and
    -1.02
     can
    -0.99
     with
    -0.96
     koş
    -0.95
     administrativo
    -0.93
    POSITIVE LOGITS
     promin
    1.15
     SPOILERS
    1.14
    牘
    1.14
     והוא
    1.14
     apparaissent
    1.14
     intermin
    1.11
     ruines
    1.10
    γι
    1.10
    Cooperation
    1.09
    ebly
    1.08
    Activations Density 0.034%

    No Known Activations