© 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. 72097
    Prev
    Next
    INDEX
    Explanations

    selection and specific items

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

    The neuron fires on words naming tangible materials or objects (e.g. “socks,” “stuffing,” “magnesium,” “enzymes,” “laser,” etc.).

    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
    次代
    -1.00
     scrum
    -0.86
     adicionais
    -0.84
    Transcriptie
    -0.82
    Dimensi
    -0.82
    Witam
    -0.82
    יסט
    -0.82
    倖
    -0.81
     further
    -0.81
    Transcripción
    -0.80
    POSITIVE LOGITS
     χρησιμοποι
    1.33
     used
    1.27
     chosen
    1.20
    chosen
    1.14
     choice
    1.13
    laß
    1.09
     choices
    1.06
     použ
    1.05
    mişti
    1.05
    ?}",
    1.05
    Activations Density 0.081%

    No Known Activations