© 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. 10-GEMMASCOPE-RES-131K
    7. 48209
    Prev
    Next
    INDEX
    Explanations

    necessary directions

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

    The neuron strongly activates on procedural or instructional passages—recognizing “how‐to” language (steps, conditions, modals like can/be/should) in a text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     coloris
    -1.70
    beding
    -1.48
    llten
    -1.34
    荭
    -1.34
     fallu
    -1.32
    herself
    -1.31
    Phaser
    -1.30
    outed
    -1.30
    datable
    -1.29
    🚒
    -1.28
    POSITIVE LOGITS
     you
    2.05
     this
    1.99
     like
    1.54
     now
    1.48
     here
    1.45
     of
    1.41
     have
    1.35
     so
    1.31
     know
    1.27
     hauptsächlich
    1.26
    Activations Density 0.033%

    No Known Activations