© 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. 22-GEMMASCOPE-RES-131K
    7. 26385
    Prev
    Next
    INDEX
    Explanations

    positive sentiment and anticipation

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

    The neuron fires on strong positive sentiment words and expressions of enthusiasm (e.g. delighted, proud, grateful, excited, overjoyed).

    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
     several
    -1.31
     some
    -1.22
     many
    -1.16
     even
    -1.15
     just
    -1.12
     my
    -1.12
     something
    -1.03
     créé
    -1.03
     two
    -1.01
    красивые
    -1.01
    POSITIVE LOGITS
    ホルモン
    1.14
     peculiarities
    1.14
     tejto
    1.13
     fredag
    1.11
    该如何
    1.10
     tohto
    1.10
     amethyst
    1.09
     zoll
    1.08
     Khart
    1.07
    yd
    1.05
    Activations Density 0.004%

    No Known Activations