© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 22089
    Prev
    Next
    INDEX
    Explanations

    hit a snag

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

    This neuron detects idiomatic “encounter” phrases where someone “hits a … ” or “runs into a …,” i.e. running into obstacles or problems.

    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
     to
    -1.93
    simply
    -1.29
    
    -1.23
     senza
    -1.20
     Beobach
    -1.18
     Number
    -1.16
    owulf
    -1.14
     Versuche
    -1.13
    了许多
    -1.12
     kaban
    -1.12
    POSITIVE LOGITS
     with
    1.47
    transQ
    1.42
     tuvimos
    1.30
    Gentile
    1.28
     where
    1.24
     ubicado
    1.22
    点此
    1.22
     fuimos
    1.18
     wyboru
    1.18
     crossroads
    1.17
    Activations Density 0.043%

    No Known Activations