© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62990
    Prev
    Next
    INDEX
    Explanations

    defendants in legal cases

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

    This neuron activates on code-indentation whitespace (e.g. leading spaces or tabs at the start of lines).

    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
     return
    -5.97
    return
    -5.72
     returned
    -4.34
     returns
    -4.31
     Return
    -4.19
     returning
    -4.16
    Return
    -3.88
     RETURN
    -3.61
    返回
    -3.38
     возвра
    -3.38
    POSITIVE LOGITS
    ongono
    0.75
    fordshire
    0.74
    RemoveField
    0.69
    embang
    0.68
    िल्
    0.68
    🚪
    0.66
    цю
    0.66
     vidas
    0.66
    mbangan
    0.65
    alena
    0.65
    Activations Density 0.099%

    No Known Activations