© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49792
    Prev
    Next
    INDEX
    Explanations

    many followed by a group

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

    The neuron responds to words expressing large quantities or counts (e.g. “many”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    wesenheit
    -1.20
    volles
    -1.18
    鵙
    -1.16
    tellers
    -1.16
    nibus
    -1.15
     ***!
    -1.12
    ÓD
    -1.11
     хоте
    -1.09
     ducha
    -1.09
     några
    -1.08
    POSITIVE LOGITS
     in
    2.63
     of
    2.55
     within
    2.03
     believe
    1.82
     have
    1.68
     feel
    1.63
     who
    1.63
     felt
    1.53
     believed
    1.46
     would
    1.45
    Activations Density 0.051%

    No Known Activations