© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 65274
    Prev
    Next
    INDEX
    Explanations

    following verbs or prepositions

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

    This neuron is tracking how far into the text you are—its activation steadily rises with the token’s position in the document.

    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
    Argu
    -1.34
    Needless
    -1.14
     فى
    -1.09
     émer
    -1.06
    ținut
    -1.05
     applau
    -1.05
     apprécier
    -1.05
     disgruntled
    -1.04
     généralement
    -1.02
     dessinée
    -1.02
    POSITIVE LOGITS
     which
    1.18
     tiredness
    1.16
     concerning
    1.12
     besides
    1.11
     regarding
    1.10
     evidently
    1.10
     especially
    1.08
     because
    1.07
     possibilities
    1.07
    ったのは
    1.06
    Activations Density 0.389%

    No Known Activations