© 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. 7662
    Prev
    Next
    INDEX
    Explanations

    SSD and related acronyms

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

    The neuron activates on the acronym “SSD,” i.e. references to solid-state drives.

    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
    尛
    -3.14
    呿
    -2.78
    衚
    -2.70
     uſed
    -2.56
    媜
    -2.50
    狷
    -2.42
    臯
    -2.42
    年
    -2.41
     Salón
    -2.41
    atisfaction
    -2.41
    POSITIVE LOGITS
    ’
    3.02
     и
    2.48
     şi
    2.42
    ron
    2.34
    with
    2.34
    and
    2.22
    I
    2.16
     và
    2.09
    my
    2.08
     și
    2.06
    Activations Density 0.003%

    No Known Activations