© 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. 1854
    Prev
    Next
    INDEX
    Explanations

    self + descriptors

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

    The neuron activates on occurrences of the prefix “self” (as in self-employed, self-financing, etc.).

    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
     сфере
    -0.75
     pseudo
    -0.73
    弊
    -0.72
     Discussions
    -0.70
     envelop
    -0.68
    martin
    -0.68
    lamp
    -0.68
    طل
    -0.66
    ListActivity
    -0.66
    tuna
    -0.66
    POSITIVE LOGITS
    cinta
    0.82
     trạng
    0.79
    belief
    0.79
    build
    0.75
    chalten
    0.73
     formy
    0.73
    垫
    0.73
     gunner
    0.72
     fann
    0.71
     permukaan
    0.70
    Activations Density 0.033%

    No Known Activations