© 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. 50431
    Prev
    Next
    INDEX
    Explanations

    Im\- words

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

    The neuron is highly responsive to the two-letter token “im” (as it appears at the start of words like imidase, immunity, impairment, impose, 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
    Adorable
    -0.85
    時間も
    -0.84
    لسلة
    -0.83
    cheinend
    -0.76
    Difficult
    -0.73
    Wtf
    -0.73
    Very
    -0.73
     at
    -0.72
    階段
    -0.71
    Notif
    -0.71
    POSITIVE LOGITS
     Imp
    1.20
    Imp
    1.18
     IMP
    1.13
    im
    1.02
    hoff
    1.01
     им
    1.00
     Im
    0.98
     IM
    0.97
    IMP
    0.97
    implode
    0.95
    Activations Density 0.033%

    No Known Activations