© 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. 56049
    Prev
    Next
    INDEX
    Explanations

    Welcome to the start

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

    The neuron activates on specialized environmental‐policy vocabulary—particularly terms related to chemicals, waste, waste management, and associated organizations and processes.

    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
    Event
    -0.70
    personalised
    -0.68
    Stam
    -0.68
     Sardegna
    -0.66
    pied
    -0.66
     glucocortico
    -0.66
     печати
    -0.65
     enfe
    -0.65
    жала
    -0.65
    rosis
    -0.65
    POSITIVE LOGITS
     Basel
    1.05
    Basel
    0.97
     Rotterdam
    0.95
     bans
    0.91
     Bama
    0.84
     dumped
    0.83
     Basal
    0.82
     banned
    0.82
    notin
    0.82
     hazardous
    0.80
    Activations Density 0.013%

    No Known Activations