© 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. 34-GEMMASCOPE-RES-131K
    7. 82788
    Prev
    Next
    INDEX
    Explanations

    packed with

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

    The neuron fires strongly on phrasing that emphasizes something being “packed” or “full” of features, contents, or qualities, i.e. descriptions of abundance or density (e.g. “packed with…,” “full of…”).

    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
    lindungi
    -0.91
    PROPOSED
    -0.85
    kkelijk
    -0.82
    极为
    -0.82
    sella
    -0.79
    Fernseh
    -0.77
    扱い
    -0.77
    &=&\
    -0.77
    wendi
    -0.75
     Biochem
    -0.73
    POSITIVE LOGITS
     full
    4.94
     filled
    4.72
     lleno
    3.59
    filled
    3.59
     Filled
    3.56
    full
    3.42
    Filled
    3.39
     voller
    3.33
     peł
    3.11
     penuh
    3.06
    Activations Density 0.154%

    No Known Activations