© 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. 68875
    Prev
    Next
    INDEX
    Explanations

    version versions

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

    The neuron is a “rare‐word” detector—it lights up on relatively uncommon, specialized, or domain-specific tokens rather than on high-frequency everyday words.

    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
     venge
    -1.20
     nabíd
    -1.20
     Según
    -1.19
     énorm
    -1.16
     cohe
    -1.16
     dégust
    -1.15
     anunció
    -1.13
     masterful
    -1.13
     破解
    -1.10
     bricola
    -1.09
    POSITIVE LOGITS
     version
    1.80
     versione
    1.77
     versions
    1.72
     versión
    1.70
    version
    1.43
     VERSION
    1.38
     get
    1.35
     only
    1.32
    版本的
    1.28
     find
    1.17
    Activations Density 0.159%

    No Known Activations