© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 72890
    Prev
    Next
    INDEX
    Explanations

    specific or certain quality

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

    This neuron detects language expressing plans, intentions, or hopeful expectations (e.g. “hope,” “going to,” “Maybe better …”).

    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
     только
    -1.70
     апреля
    -1.69
     мая
    -1.60
     лишь
    -1.58
     ":
    -1.52
    ième
    -1.41
     ")
    -1.41
     of
    -1.37
     июля
    -1.37
     exemplos
    -1.35
    POSITIVE LOGITS
     certain
    2.02
     there
    1.74
    にします
    1.69
    を行いました
    1.59
    をしました
    1.55
     different
    1.53
    Característica
    1.48
    Alguns
    1.47
    が必要です
    1.44
     specific
    1.43
    Activations Density 0.037%

    No Known Activations