© 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. 74575
    Prev
    Next
    INDEX
    Explanations

    showed or proved something

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

    This neuron detects verbs and verb phrases that assert demonstration or evidence (e.g. “show,” “proved,” “displayed,” “has shown,” “prove”).

    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
     these
    -1.77
     innovación
    -1.54
    因為
    -1.48
     tyd
    -1.45
    五月
    -1.44
    킵
    -1.44
     cirugía
    -1.40
     kommunik
    -1.38
     lakini
    -1.38
    เพราะ
    -1.36
    POSITIVE LOGITS
    捋
    1.60
     
    1.56
     -
    1.56
     –
    1.55
     deserves
    1.49
     durante
    1.48
    蝋
    1.46
    抵达
    1.45
     −
    1.45
     apropri
    1.45
    Activations Density 0.034%

    No Known Activations