© 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. 69033
    Prev
    Next
    INDEX
    Explanations

    actions by others

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

    The neuron flags verbs and action words that invite or describe user participation or contribution (e.g. contribute, evaluate, share, post, respond).

    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
    胯
    -1.12
     bougies
    -1.08
     Ms
    -1.07
    を用意
    -1.06
    לוס
    -1.06
    体の
    -1.05
     sonor
    -1.05
    demon
    -1.05
     KI
    -1.03
    mention
    -1.02
    POSITIVE LOGITS
     your
    1.57
     you
    1.52
    ᾿
    1.34
     zajíma
    1.27
     their
    1.19
     by
    1.19
     hvě
    1.14
     Mereka
    1.13
     discí
    1.12
    万一
    1.11
    Activations Density 0.076%

    No Known Activations