© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77486
    Prev
    Next
    INDEX
    Explanations

    variable assignment

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

    The neuron activates on shell‐style variable names (often in assignments or environment‐variable contexts) in bash scripts.

    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
    احب
    -0.98
    ホント
    -0.98
     _:
    -0.96
     الرغم
    -0.96
    ضية
    -0.91
    τούν
    -0.88
     туры
    -0.87
     Moreover
    -0.87
    しますね
    -0.87
    كال
    -0.85
    POSITIVE LOGITS
    =$
    1.88
    =
    1.82
    ="
    1.80
    }=\
    1.55
    =${
    1.32
    =(
    1.30
    ='
    1.28
    }=
    1.25
    =\
    1.24
    =`
    1.20
    Activations Density 0.042%

    No Known Activations