© 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. 22-GEMMASCOPE-RES-131K
    7. 71672
    Prev
    Next
    INDEX
    Explanations

    credit card

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

    The neuron fires on isolated non-letter symbols (such as standalone digits in version numbers or punctuation like a closing curly brace).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     évé
    -1.38
     seizoen
    -1.30
     conseille
    -1.27
     bré
    -1.27
     Automó
    -1.24
     Polskiej
    -1.22
     cerro
    -1.20
    laatst
    -1.20
     norvég
    -1.20
     réus
    -1.20
    POSITIVE LOGITS
     figliu
    1.12
     culturale
    1.09
     gegenwär
    1.09
     Coroner
    1.08
    這些
    1.05
     erwähnten
    1.05
    SOME
    1.02
    fl
    1.02
    küche
    1.02
     大きい
    1.02
    Activations Density 0.000%

    No Known Activations