© 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. 10-GEMMASCOPE-RES-131K
    7. 67347
    Prev
    Next
    INDEX
    Explanations

    checkpoint, roadblock, toll booth

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

    The neuron primarily fires on the noun “checkpoint” (including its plural form) across a wide range of contexts.

    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
    antism
    -1.34
    manteau
    -1.27
    ДА
    -1.27
    horts
    -1.27
    živ
    -1.24
     påvir
    -1.21
     überrascht
    -1.21
    .
    -1.21
    ثي
    -1.20
     ewigen
    -1.20
    POSITIVE LOGITS
    ∎
    1.44
    ik
    1.38
     autoridad
    1.37
     où
    1.36
     didn
    1.34
    corrhi
    1.33
    id
    1.33
    uk
    1.32
     différente
    1.29
     verschiedene
    1.25
    Activations Density 0.025%

    No Known Activations