© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3267
    Prev
    Next
    INDEX
    Explanations

    compound words or phrases

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

    The neuron looks for idiomatic multi‐word or hyphenated descriptive phrases (e.g. “tear-jerker,” “slow jam,” “record breaker,” “jaw-breakers,” “rib-tickling,” 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_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
    guru
    -0.84
     fortæller
    -0.79
    拠点
    -0.75
     réfléchir
    -0.74
     comprendre
    -0.74
     forklar
    -0.73
    검
    -0.73
    reis
    -0.72
     vertellen
    -0.71
     réduire
    -0.71
    POSITIVE LOGITS
     opener
    1.56
     stun
    1.43
     winner
    1.38
     burner
    1.32
     banger
    1.21
     Opener
    1.11
     topper
    1.11
     stopper
    1.08
     keeper
    1.07
     masterpiece
    1.06
    Activations Density 0.074%

    No Known Activations