© 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. 22-GEMMASCOPE-RES-131K
    7. 15062
    Prev
    Next
    INDEX
    Explanations

    historicprotection area

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

    The neuron activates on formal planning and heritage-preservation terminology, such as technical report titles (e.g. “Historic Resource Impact Study”) and protected-area designations (e.g. “Special Protection Area”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    hirts
    -1.45
     alho
    -1.37
    izamos
    -1.37
    oczes
    -1.34
     geg
    -1.30
     herbes
    -1.28
     marseille
    -1.27
     olika
    -1.24
     kutoka
    -1.22
    ztes
    -1.22
    POSITIVE LOGITS
     potentially
    1.63
     or
    1.56
     potential
    1.48
    Those
    1.44
    ֶּ
    1.32
     significant
    1.29
     protect
    1.26
    ｷ
    1.23
     noted
    1.22
    ﾋ
    1.22
    Activations Density 0.010%

    No Known Activations