© 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. 54307
    Prev
    Next
    INDEX
    Explanations

    positive emotions and states

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

    The neuron fires on subjective, first‐person or testimonial language—i.e. personal pronouns (“I’m,” “we are,” “our clients”) and positive evaluative words expressing feelings or endorsements.

    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
    corrhi
    -1.22
    avond
    -1.21
     interessantes
    -1.17
    consejos
    -1.16
    が無い
    -1.15
     before
    -1.14
    haviours
    -1.14
    zember
    -1.13
     ilumina
    -1.11
     bekämp
    -1.11
    POSITIVE LOGITS
     also
    1.40
     glad
    1.24
    de
    1.17
    ā
    1.05
    <!--
    1.05
    </em>
    1.04
    \|
    1.03
     grateful
    1.01
    They
    1.00
    ‐
    1.00
    Activations Density 0.014%

    No Known Activations