© 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. 66154
    Prev
    Next
    INDEX
    Explanations

    unsigned NOT NULL

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

    This neuron is keyed to the standalone "s" suffix (the ’s possessive/marker token).

    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
    OrNull
    -0.83
    oide
    -0.82
    spam
    -0.80
    ?}",
    -0.79
    tovní
    -0.77
    itions
    -0.76
    ształ
    -0.75
    magyar
    -0.73
    goth
    -0.73
    //!
    
    -0.72
    POSITIVE LOGITS
    iry
    0.76
    StringField
    0.73
     Heather
    0.73
    ġġ
    0.73
     place
    0.73
    ooplankton
    0.71
    ቹ
    0.71
     Springs
    0.71
    んです
    0.70
    OGUE
    0.70
    Activations Density 0.001%

    No Known Activations