© 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. 59270
    Prev
    Next
    INDEX
    Explanations

    Vita, Guggenheim, CCA, Capo

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

    This neuron specializes in spotting mentions of Sony’s handheld gaming systems—especially “PS Vita” (and occasionally “PSP”).

    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
    踅
    -2.88
    梘
    -2.86
    '
    -2.77
    _
    -2.64
    d
    -2.38
    
    -2.34
    咵
    -2.33
     blusa
    -2.28
    葙
    -2.25
    </i>
    -2.20
    POSITIVE LOGITS
    _{
    2.63
    是
    2.56
     PSP
    2.53
     There
    2.52
    可以说
    2.41
     Because
    2.38
    $,
    2.27
     ส่วน
    2.20
    —
    2.17
     It
    2.16
    Activations Density 0.004%

    No Known Activations