© 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. 10-GEMMASCOPE-RES-131K
    7. 43021
    Prev
    Next
    INDEX
    Explanations

    sounds like

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

    The neuron fires strongly on the phrase “sounds like” (i.e. instances of someone making a perceptual or evaluative comparison).

    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
     Moderato
    -1.21
    beca
    -1.17
     Эти
    -1.16
     다른
    -1.15
    taglio
    -1.13
     lemb
    -1.12
    parently
    -1.12
     dié
    -1.11
     don
    -1.11
     lieve
    -1.09
    POSITIVE LOGITS
     if
    1.29
     なら
    1.26
     at
    1.17
     a
    1.12
     entonces
    1.09
     from
    1.09
     options
    1.09
    macam
    1.08
     salaries
    1.05
     original
    1.05
    Activations Density 0.038%

    No Known Activations