© 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. 10-GEMMASCOPE-RES-131K
    7. 102655
    Prev
    Next
    INDEX
    Explanations

    to be

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

    The neuron fires on occurrences of “needs” (and closely related requirement phrasing).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     patienter
    -2.13
     nahil
    -2.11
     zoude
    -2.09
     mauva
    -2.06
    慙
    -2.00
    鰨
    -1.97
    
    -1.96
     Création
    -1.92
     dezelve
    -1.91
    이며
    -1.88
    POSITIVE LOGITS
     be
    2.38
     S
    1.59
     ans
    1.55
     besonders
    1.52
    ):
    1.50
     pal
    1.48
    子が
    1.46
     something
    1.45
     G
    1.45
    solete
    1.45
    Activations Density 0.012%

    No Known Activations