© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 44995
    Prev
    Next
    INDEX
    Explanations

    Pandas or tenant farms

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

    The neuron flags any token containing the substring “pand” (e.g. in “Pand,” “pandas,” “pandera,” 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
    饹
    -3.25
     praca
    -3.02
    ᯅ
    -2.97
    俛
    -2.95
     zoude
    -2.91
     veze
    -2.89
    êmio
    -2.88
    齪
    -2.86
    
    -2.84
    嫪
    -2.83
    POSITIVE LOGITS
    when
    2.89
     
    2.86
    '
    2.83
    Have
    2.78
     There
    2.61
    </h3>
    2.47
    With
    2.44
    Since
    2.42
    Although
    2.39
    Not
    2.38
    Activations Density 0.007%

    No Known Activations