© 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. 34-GEMMASCOPE-RES-131K
    7. 107225
    Prev
    Next
    INDEX
    Explanations

    attempt to

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

    The neuron responds to strong evaluative or emphasis words—comparatives, superlatives, and necessity markers (e.g. better, more, critical, especially) that signal importance or urgency.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     потом
    -1.02
     acepción
    -0.99
    丽
    -0.95
    тся
    -0.94
     kompetisi
    -0.93
     ακόμα
    -0.92
    是没有
    -0.90
    istet
    -0.90
     dizaine
    -0.90
     blir
    -0.85
    POSITIVE LOGITS
     XNUMX
    1.53
     storey
    1.48
     necessitates
    1.42
    Numerous
    1.30
     hingegen
    1.30
     yalnızca
    1.28
    さまざまな
    1.27
    Examine
    1.27
     Examine
    1.27
     العديد
    1.27
    Activations Density 0.064%

    No Known Activations