© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 98646
    Prev
    Next
    INDEX
    Explanations

    waiting for godot

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

    The neuron fires on words that are part of titles or headings (e.g. the names of plays, works, or proper‐name phrases).

    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
    Scienti
    -0.73
     Haw
    -0.73
    あっという
    -0.70
    Wg
    -0.69
    ielsen
    -0.69
     assemble
    -0.68
     hornear
    -0.68
    Lawyer
    -0.67
    磯
    -0.65
    Phal
    -0.63
    POSITIVE LOGITS
     Beckett
    1.42
    Samuel
    1.07
    Vladimir
    1.05
     Vladimir
    0.99
    Beck
    0.95
     Samuel
    0.92
     Endgame
    0.92
     Didi
    0.85
    emptyList
    0.81
    렘
    0.81
    Activations Density 0.015%

    No Known Activations