© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 103687
    Prev
    Next
    INDEX
    Explanations

    Hamcrest library

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

    The neuron fires on numeric tokens (i.e. sequences of digits) such as literal numbers or version/file identifiers.

    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
     moderately
    -1.23
     straightforward
    -1.20
     interestingly
    -1.12
     strangely
    -1.10
     gydy
    -1.09
     intensely
    -1.09
     presumably
    -1.07
     strongly
    -1.07
     difficult
    -1.05
    OCUS
    -1.05
    POSITIVE LOGITS
    accharide
    0.90
    そして
    0.90
    iferous
    0.88
     Futsal
    0.87
     レア
    0.87
     DIRECTORY
    0.85
    جعل
    0.85
    それにしても
    0.84
    lograph
    0.84
    شنامه
    0.84
    Activations Density 0.096%

    No Known Activations