© 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. 10-GEMMASCOPE-RES-131K
    7. 85190
    Prev
    Next
    INDEX
    Explanations

    imager, Imam, iMac, Iman

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

    This neuron activates strongly on any token containing the substring “ima” (e.g. “iMac,” “ima,” “imager,” “imake,” 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_10/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
    ,”
    -2.80
    ].
    -2.45
     Schülern
    -2.44
    .’
    -2.38
     ellos
    -2.33
    ，
    -2.33
     verschied
    -2.31
    ,\
    -2.31
     Mitarbeitern
    -2.30
    窍
    -2.27
    POSITIVE LOGITS
    欝
    2.16
     hermanas
    2.16
    鐽
    2.14
     sympathi
    2.09
    栳
    2.08
    鱟
    2.06
    皷
    2.02
     所以
    2.00
     seep
    1.97
     当
    1.95
    Activations Density 0.005%

    No Known Activations