© 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. 63507
    Prev
    Next
    INDEX
    Explanations

    boolean values, yes/no, true/false

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

    The neuron fires on numeric tokens (number literals) in code or tabular data.

    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
    gewöhn
    -1.11
    дарю
    -1.02
    rably
    -1.02
    haviours
    -1.00
    Pune
    -0.98
    danke
    -0.98
     selera
    -0.98
    );\
    -0.98
    Também
    -0.96
     spiaggia
    -0.96
    POSITIVE LOGITS
     largely
    1.34
     mixed
    1.23
     yes
    1.22
     mostly
    1.16
     partial
    1.13
     neither
    1.03
     limited
    1.02
     partially
    1.02
    ?
    1.00
     depending
    0.99
    Activations Density 0.024%

    No Known Activations