© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78097
    Prev
    Next
    INDEX
    Explanations

    in a state of

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

    The neuron fires on single-word abstract nouns that denote a state, condition, or situation (e.g. shock, default, limbo, disarray, celebration, peril).

    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
     in
    -0.99
    ให้
    -0.88
    begin
    -0.88
     Anerkennung
    -0.85
     into
    -0.84
     devout
    -0.84
     ensuing
    -0.84
    งาน
    -0.80
     Vorstellungen
    -0.79
     Wurzeln
    -0.79
    POSITIVE LOGITS
     mode
    1.55
     زیرا
    1.14
     limbo
    1.09
    mode
    1.09
     MODE
    1.06
    他已经
    1.02
    之中
    0.97
     position
    0.94
    ution
    0.93
    状态
    0.93
    Activations Density 0.089%

    No Known Activations