© 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. 15206
    Prev
    Next
    INDEX
    Explanations

    these, them, these, those

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

    The neuron flags whichever token is the single most frequent (i.e. highest‐count) word in each text segment.

    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
    вшей
    -0.95
    vų
    -0.92
    ⋗
    -0.84
     secundario
    -0.84
     bà
    -0.84
    Myself
    -0.84
    łania
    -0.83
    Buna
    -0.82
     других
    -0.82
     cinema
    -0.82
    POSITIVE LOGITS
     these
    1.90
     each
    1.62
    這些
    1.31
    这些
    1.26
    These
    1.20
     them
    1.18
    these
    1.17
    該
    1.09
     such
    1.07
     kaž
    1.05
    Activations Density 0.141%

    No Known Activations