© 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. 22-GEMMASCOPE-RES-131K
    7. 66246
    Prev
    Next
    INDEX
    Explanations

    necessity and wanting

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

    The neuron is detecting sentence boundaries—strongly activating on end-of-sentence punctuation (periods, ellipses) and the first words or transition words that start new sentences.

    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
    fillment
    -0.94
    itability
    -0.93
    riedenheit
    -0.93
     felpa
    -0.89
    :"-
    -0.88
    nisses
    -0.87
    ₁(
    -0.87
    rufen
    -0.85
    IVITY
    -0.85
    eriksaan
    -0.84
    POSITIVE LOGITS
     needed
    1.49
     necessity
    1.24
     necessary
    1.23
     Needed
    1.13
     it
    1.12
     wanted
    1.11
    เพื่อ
    1.09
     necessitated
    1.07
     need
    1.05
    needed
    1.03
    Activations Density 0.062%

    No Known Activations