© 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. 34239
    Prev
    Next
    INDEX
    Explanations

    periods and states

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

    This neuron detects mentions of quantitative data, i.e. numerical statistics and counts.

    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
     verschillende
    -1.31
     inoltre
    -1.16
    了一些
    -1.13
     sommige
    -1.11
     inilah
    -1.07
    érrez
    -1.04
    踅
    -1.02
     eventuell
    -1.02
     scuro
    -1.01
    Musique
    -1.00
    POSITIVE LOGITS
    ).
    1.20
     semelhantes
    1.10
     despite
    1.10
    Toeschouwers
    1.05
     unlike
    1.04
     to
    1.03
     anyway
    1.02
     due
    1.00
     and
    0.98
     bArr
    0.97
    Activations Density 0.149%

    No Known Activations