© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72794
    Prev
    Next
    INDEX
    Explanations

    license agreement

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

    This neuron fires on uncommon, domain‐specific content words (e.g. “resources,” “hexyl,” “user,” “security,” “doc,” etc.).

    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
    훌
    -1.52
     APPELLATE
    -1.38
    îtra
    -1.34
    那时
    -1.31
     若
    -1.30
     densité
    -1.29
    を外
    -1.29
     fréquence
    -1.27
     hivyo
    -1.27
    énus
    -1.26
    POSITIVE LOGITS
     These
    1.99
    These
    1.77
    0
    1.69
    these
    1.65
     döner
    1.55
    醅
    1.51
     klingt
    1.48
     dasarnya
    1.46
    之地
    1.46
     newest
    1.46
    Activations Density 0.001%

    No Known Activations