© 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. 22-GEMMASCOPE-RES-131K
    7. 67523
    Prev
    Next
    INDEX
    Explanations

    in places

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

    This neuron does not respond to any tokens—it appears to be inactive (a “dead” neuron).

    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
    jatel
    -1.41
     てき
    -1.29
    Vezi
    -1.26
    mdash
    -1.24
    놋
    -1.21
    菝
    -1.20
     cambiado
    -1.19
     också
    -1.18
     россии
    -1.17
    continence
    -1.15
    POSITIVE LOGITS
     other
    1.81
     those
    1.71
     these
    1.68
     each
    1.62
     our
    1.44
     both
    1.35
     some
    1.34
     any
    1.33
     only
    1.32
     more
    1.30
    Activations Density 0.077%

    No Known Activations