© 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. 34-GEMMASCOPE-RES-131K
    7. 98618
    Prev
    Next
    INDEX
    Explanations

    code and technical text

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

    The neuron activates on C/C++ preprocessor “#include” lines (i.e. header‐file inclusion directives).

    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
     and
    -0.74
    aerial
    -0.72
    nyx
    -0.71
    ਹ
    -0.70
     آدم
    -0.68
    vskip
    -0.67
     Abundance
    -0.67
    ની
    -0.66
     suelen
    -0.66
    转换成
    -0.66
    POSITIVE LOGITS
    mutable
    1.09
     mutable
    0.99
     телефону
    0.91
    Mutable
    0.86
    }))
    0.86
    hage
    0.82
     SYLLABLE
    0.81
    中央
    0.79
    Cylinder
    0.78
    ()->
    0.78
    Activations Density 0.026%

    No Known Activations